Practical Bayesian Optimization of Machine Learning Algorithms

Abstract

Machine learning algorithms frequently require careful tuning of model hyperparameters, regularization terms, and optimization parameters. Unfortunately, this tuning is often a "black art" that requires expert experience, unwritten rules of thumb, or sometimes brute-force search. Much more appealing is the idea of developing automatic approaches which can optimize the performance of a given learning algorithm to the task at hand. In this work, we consider the automatic tuning problem within the framework of Bayesian optimization, in which a learning algorithm's generalization performance is modeled as a sample from a Gaussian process (GP). The tractable posterior distribution induced by the GP leads to efficient use of the information gathered by previous experiments, enabling optimal choices about what parameters to try next. Here we show how the effects of the Gaussian process prior and the associated inference procedure can have a large impact on the success or failure of Bayesian optimization. We show that thoughtful choices can lead to results that exceed expert-level performance in tuning machine learning algorithms. We also describe new algorithms that take into account the variable cost (duration) of learning experiments and that can leverage the presence of multiple cores for parallel experimentation. We show that these proposed algorithms improve on previous automatic procedures and can reach or surpass human expert-level optimization on a diverse set of contemporary algorithms including latent Dirichlet allocation, structured SVMs and convolutional neural networks.

References in corpus (2)

• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• Slice sampling covariance hyperparameters of latent Gaussian models

Cited by in corpus (942)

• A Survey on Deep Learning in Medical Image Analysis
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• LSTM: A Search Space Odyssey
• On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• AutoML: A Survey of the State-of-the-Art
• Machine Learning Force Fields
• Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions
• A Survey on Distributed Machine Learning
• Challenges in Deploying Machine Learning: a Survey of Case Studies
• Tensorizing Neural Networks
• Tune: A Research Platform for Distributed Model Selection and Training
• Regularized Deep Networks in Intelligent Transportation Systems: A Taxonomy and a Case Study
• Compressing Neural Networks with the Hashing Trick
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Large-Scale Evolution of Image Classifiers
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• Scalable Bayesian Optimization Using Deep Neural Networks
• Towards Robust Interpretability with Self-Explaining Neural Networks
• Predictive Entropy Search for Efficient Global Optimization of Black-box Functions
• Generative Moment Matching Networks
• A Tutorial on Bayesian Optimization
• Hyperparameter Search in Machine Learning
• Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
• Rice Diseases Detection and Classification Using Attention Based Neural Network and Bayesian Optimization
• Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets
• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning
• Dealing with Integer-valued Variables in Bayesian Optimization with Gaussian Processes
• BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
• Dealing with Categorical and Integer-valued Variables in Bayesian Optimization with Gaussian Processes
• Multi-Stage Optimized Machine Learning Framework for Network Intrusion Detection
• Neural Architecture Search with Bayesian Optimisation and Optimal Transport
• Machine Learning in Nuclear Physics
• BayesOpt: A Bayesian Optimization Library for Nonlinear Optimization, Experimental Design and Bandits
• Jet Substructure Classification in High-Energy Physics with Deep Neural Networks
• Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
• Random Search and Reproducibility for Neural Architecture Search
• Bayesian optimization for materials design
• CMA-ES for Hyperparameter Optimization of Deep Neural Networks
• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
• Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
• LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns
• Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System
• Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
• Artificial Intelligence for Satellite Communication: A Review
• On Empirical Comparisons of Optimizers for Deep Learning
• Learning to Optimize Tensor Programs
• Spectral Representations for Convolutional Neural Networks
• A deep learning enabler for non-intrusive reduced order modeling of fluid flows
• Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge
• Online Batch Selection for Faster Training of Neural Networks
• Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020
• Progressive Neural Architecture Search
• Data-driven polynomial chaos expansion for machine learning regression
• Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
• How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
• Deep Learning on FPGAs: Past, Present, and Future
• Learning to Optimize
• Automated Machine Learning: State-of-The-Art and Open Challenges
• Multi-task Neural Networks for QSAR Predictions
• A Framework to Integrate Mode Choice in the Design of Mobility-on-Demand Systems
• TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensors
• DeepArchitect: Automatically Designing and Training Deep Architectures
• Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review
• Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets
• A Convolutional Attention Network for Extreme Summarization of Source Code
• An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
• Student-t Processes as Alternatives to Gaussian Processes
• AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
• High Dimensional Bayesian Optimisation and Bandits via Additive Models
• Greed is Good: Exploration and Exploitation Trade-offs in Bayesian Optimisation
• Deep Learning: A Bayesian Perspective
• A new Taxonomy of Continuous Global Optimization Algorithms
• Neural Additive Models: Interpretable Machine Learning with Neural Nets
• Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models
• Pricing options and computing implied volatilities using neural networks
• Testing Scenario Library Generation for Connected and Automated Vehicles: An Adaptive Framework
• Predictive Entropy Search for Bayesian Optimization with Unknown Constraints
• Representation Learning: A Review and New Perspectives
• Scale-Invariant Convolutional Neural Networks
• Data-efficient Auto-tuning with Bayesian Optimization: An Industrial Control Study
• Dataset Condensation with Gradient Matching
• Do Deep Convolutional Nets Really Need to be Deep and Convolutional?
• Bilevel Programming for Hyperparameter Optimization and Meta-Learning
• Long-time predictive modeling of nonlinear dynamical systems using neural networks
• Short-segment heart sound classification using an ensemble of deep convolutional neural networks
• Bayesian Hyperparameter Optimization for Deep Neural Network-Based Network Intrusion Detection
• Stochastic analysis of heterogeneous porous material with modified neural architecture search (NAS) based physics-informed neural networks using transfer learning
• Early Detection of Parkinson's Disease through Patient Questionnaire and Predictive Modelling
• Bayesian optimization package: PHYSBO
• IoT Data Analytics in Dynamic Environments: From An Automated Machine Learning Perspective
• GPS-ABC: Gaussian Process Surrogate Approximate Bayesian Computation
• Deep Convolutional Networks as shallow Gaussian Processes
• RNADE: The real-valued neural autoregressive density-estimator
• Input Warping for Bayesian Optimization of Non-stationary Functions
• The Automatic Neuroscientist: automated experimental design with real-time fMRI
• Programmatically Interpretable Reinforcement Learning
• Understanding the effect of hyperparameter optimization on machine learning models for structure design problems
• Evolutionary Reinforcement Learning: A Survey
• Adaptation Strategies for Automated Machine Learning on Evolving Data
• OBOE: Collaborative Filtering for AutoML Model Selection
• A meta-learning recommender system for hyperparameter tuning: predicting when tuning improves SVM classifiers
• Generalized Inner Loop Meta-Learning
• Improving Deep Neural Networks with Probabilistic Maxout Units
• Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Models
• Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search
• Learning values across many orders of magnitude
• ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
• Meta-Learning Update Rules for Unsupervised Representation Learning
• A machine learning approach for efficient uncertainty quantification using multiscale methods
• Autotune: A Derivative-free Optimization Framework for Hyperparameter Tuning
• SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
• Auto-Keras: An Efficient Neural Architecture Search System
• Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm
• TensorDash: Exploiting Sparsity to Accelerate Deep Neural Network Training and Inference
• Stochastic Hyperparameter Optimization through Hypernetworks
• Learning to Optimize Neural Nets
• Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints
• Escaping local minima with derivative-free methods: a numerical investigation
• Bayesian Optimization with Exponential Convergence
• Progressive Sampling-Based Bayesian Optimization for Efficient and Automatic Machine Learning Model Selection
• Online Learning Rate Adaptation with Hypergradient Descent
• On the Robustness of Interpretability Methods
• Weighted Random Search for CNN Hyperparameter Optimization
• Bayesian Optimization of Combinatorial Structures
• On The Effects Of Data Normalisation For Domain Adaptation On EEG Data
• Missing Data Imputation for Supervised Learning
• Parameter Optimization and Learning in a Spiking Neural Network for UAV Obstacle Avoidance targeting Neuromorphic Processors
• Differential Evolution and Bayesian Optimisation for Hyper-Parameter Selection in Mixed-Signal Neuromorphic Circuits Applied to UAV Obstacle Avoidance
• Vecchia approximations of Gaussian-process predictions
• A class of multi-resolution approximations for large spatial datasets
• Automated Machine Learning on Graphs: A Survey
• pySOT and POAP: An event-driven asynchronous framework for surrogate optimization
• Multi-Fidelity Cost-Aware Bayesian Optimization
• Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS
• Bayesian Optimization for Machine Learning : A Practical Guidebook
• Reservoir computing model of two-dimensional turbulent convection
• Federated Multi-view Matrix Factorization for Personalized Recommendations
• A System for Massively Parallel Hyperparameter Tuning
• Bayesian Multi-Scale Optimistic Optimization
• Deep Feature Learning for EEG Recordings
• Fast differentiable DNA and protein sequence optimization for molecular design
• Stochastic Physics-Informed Neural Ordinary Differential Equations
• Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction
• Parallel Bayesian Global Optimization of Expensive Functions
• Variational Auto-encoded Deep Gaussian Processes
• ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations
• Greenhouse Gas Emission Prediction on Road Network using Deep Sequence Learning
• Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions
• Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization
• A Genetic Programming Approach to Designing Convolutional Neural Network Architectures
• Towards Dynamic and Safe Configuration Tuning for Cloud Databases
• Bayesian Optimization with Output-Weighted Optimal Sampling
• Do We Need Zero Training Loss After Achieving Zero Training Error?
• Machine learning thermal circuit network model for thermal design optimization of electronic circuit board layout with transient heating chips
• Active emulation of computer codes with Gaussian processes -- Application to remote sensing
• MaskConnect: Connectivity Learning by Gradient Descent
• Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation
• AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning
• Linear Multiple Low-Rank Kernel Based Stationary Gaussian Processes Regression for Time Series
• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
• GLASSES: Relieving The Myopia Of Bayesian Optimisation
• Easy Hyperparameter Search Using Optunity
• Semi-supervised detection of structural damage using Variational Autoencoder and a One-Class Support Vector Machine
• Multi-Objective Bayesian Optimization for Accelerator Tuning
• Forward and Reverse Gradient-Based Hyperparameter Optimization
• Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces
• Alpha MAML: Adaptive Model-Agnostic Meta-Learning
• Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
• Restructuring Batch Normalization to Accelerate CNN Training
• Traffic Data Imputation using Deep Convolutional Neural Networks
• FiNER: Financial Numeric Entity Recognition for XBRL Tagging
• ENTMOOT: A Framework for Optimization over Ensemble Tree Models
• Constrained Bayesian Optimization for Automatic Chemical Design
• Stochastic Zeroth-order Optimization in High Dimensions
• Learning Compositional Koopman Operators for Model-Based Control
• Unbiased and Efficient Log-Likelihood Estimation with Inverse Binomial Sampling
• Towards Green Automated Machine Learning: Status Quo and Future Directions
• Bayesian optimization under mixed constraints with a slack-variable augmented Lagrangian
• AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
• Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble
• Omnivore: An Optimizer for Multi-device Deep Learning on CPUs and GPUs
• Gaussian Process Optimization with Mutual Information
• Global Optimization of Gaussian processes
• Quantum Embedding Search for Quantum Machine Learning
• Certified Adversarial Robustness for Deep Reinforcement Learning
• Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly
• Variational approach for learning Markov processes from time series data
• A Unifying Framework for Gaussian Process Pseudo-Point Approximations using Power Expectation Propagation
• Conformal Prediction Under Feedback Covariate Shift for Biomolecular Design
• Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection
• Product Kernel Interpolation for Scalable Gaussian Processes
• Learning Continuous Semantic Representations of Symbolic Expressions
• Differentiable Compositional Kernel Learning for Gaussian Processes
• Optimizing Millions of Hyperparameters by Implicit Differentiation
• High-Dimensional Bayesian Optimization with Sparse Axis-Aligned Subspaces
• Online AutoML: An adaptive AutoML framework for online learning
• Finite volume method network for acceleration of unsteady computational fluid dynamics: non-reacting and reacting flows
• Learning the Effect of Registration Hyperparameters with HyperMorph
• Inverse Design of Composite Metal Oxide Optical Materials based on Deep Transfer Learning
• Joint Entity Extraction and Assertion Detection for Clinical Text
• An Entropy Search Portfolio for Bayesian Optimization
• Bayesian Optimization for Synthetic Gene Design
• General solutions for nonlinear differential equations: a rule-based self-learning approach using deep reinforcement learning
• Bayesian Hyperparameter Optimization for Ensemble Learning
• Predicting online user behaviour using deep learning algorithms
• Event generator tuning using Bayesian optimization
• Combining Static and Dynamic Features for Multivariate Sequence Classification
• Gradientless Descent: High-Dimensional Zeroth-Order Optimization
• A deep-learning search for technosignatures of 820 nearby stars
• Bayesian Optimization with Adaptive Kernels for Robot Control
• Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer
• DeepTraffic: Crowdsourced Hyperparameter Tuning of Deep Reinforcement Learning Systems for Multi-Agent Dense Traffic Navigation
• Unsupervised Model Selection for Variational Disentangled Representation Learning
• Federated Learning with Buffered Asynchronous Aggregation
• Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining
• Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization
• A Population-based Hybrid Approach to Hyperparameter Optimization for Neural Networks
• Preferential Bayesian Optimization
• Efficient acquisition rules for model-based approximate Bayesian computation
• FLAML: A Fast and Lightweight AutoML Library
• t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning
• Time-Varying Gaussian Process Bandit Optimization
• Hyp-RL : Hyperparameter Optimization by Reinforcement Learning
• Emulation as an Accurate Alternative to Interpolation in Sampling Radiative Transfer Codes
• Self-Optimizing Grinding Machines using Gaussian Process Models and Constrained Bayesian Optimization
• Revisiting Bayesian Optimization in the light of the COCO benchmark
• DecomposeMe: Simplifying ConvNets for End-to-End Learning
• On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
• Finding Competitive Network Architectures Within a Day Using UCT
• Sample-Efficient Neural Architecture Search by Learning Action Space
• Batched Gaussian Process Bandit Optimization via Determinantal Point Processes
• PRADA: Protecting against DNN Model Stealing Attacks
• Neural Graph Evolution: Towards Efficient Automatic Robot Design
• Tabular Benchmarks for Joint Architecture and Hyperparameter Optimization
• Hyperparameter Ensembles for Robustness and Uncertainty Quantification
• Exact Gaussian Processes on a Million Data Points
• SentiCap: Generating Image Descriptions with Sentiments
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations
• Dynamic Clustering via Asymptotics of the Dependent Dirichlet Process Mixture
• Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science
• Machine Learning based prediction of noncentrosymmetric crystal materials
• Solving Bayesian Inverse Problems via Variational Autoencoders
• The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models
• Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling
• Automatic Composition and Optimization of Multicomponent Predictive Systems With an Extended Auto-WEKA
• Cost-aware Bayesian Optimization
• One-Shot Learning of Stochastic Differential Equations with Data Adapted Kernels
• Scalable Bayesian Inference for Excitatory Point Process Networks
• Phase diagram and optimal control for n-tupling discrete time crystal
• Sandwiching the marginal likelihood using bidirectional Monte Carlo
• The impact of social influence in Australian real-estate: market forecasting with a spatial agent-based model
• Adversarial Multi-task Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equations
• Variational Bayesian Monte Carlo with Noisy Likelihoods
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Bayesian optimization for computationally extensive probability distributions
• Adaptive Filters in Graph Convolutional Neural Networks
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing---and Back
• Automating biomedical data science through tree-based pipeline optimization
• Machine Learning Workflow to Explain Black-box Models for Early Alzheimer's Disease Classification Evaluated for Multiple Datasets
• Efficient Automatic CASH via Rising Bandits
• Deep Neural Network Hyperparameter Optimization with Orthogonal Array Tuning
• HybNet: A Hybrid Deep Learning -- Matched Filter Approach for IoT Signal Detection
• AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
• A comparison of optimisation algorithms for high-dimensional particle and astrophysics applications
• Implicit differentiation of Lasso-type models for hyperparameter optimization
• Adaptive Hamiltonian and Riemann Manifold Monte Carlo Samplers
• A Stratified Analysis of Bayesian Optimization Methods
• VisEvol: Visual Analytics to Support Hyperparameter Search through Evolutionary Optimization
• A directional Gaussian smoothing optimization method for computational inverse design in nanophotonics
• On the discriminative power of Hyper-parameters in Cross-Validation and how to choose them
• Heteroscedastic Treed Bayesian Optimisation
• Black-box Adversarial Attacks with Bayesian Optimization
• Calibrating Path Choices and Train Capacities for Urban Rail Transit Simulation Models Using Smart Card and Train Movement Data
• Overpruning in Variational Bayesian Neural Networks
• Understanding Deep Architectures using a Recursive Convolutional Network
• Matérn Gaussian processes on Riemannian manifolds
• Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning
• CheMixNet: Mixed DNN Architectures for Predicting Chemical Properties using Multiple Molecular Representations
• Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack
• Fast Cross-Validation via Sequential Testing
• Stopping criteria for boosting automatic experimental design using real-time fMRI with Bayesian optimization
• Asteroid Flyby Cycler Trajectory Design Using Deep Neural Networks
• Incorporating Expert Prior in Bayesian Optimisation via Space Warping
• Gait learning for soft microrobots controlled by light fields
• Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
• Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning
• Differentially Private Bayesian Optimization
• Black-Box Optimization with Local Generative Surrogates
• On the Iteration Complexity of Hypergradient Computation
• Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
• Learning to Warm-Start Bayesian Hyperparameter Optimization
• RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network
• Multi-fidelity Bayesian Optimization with Max-value Entropy Search and its parallelization
• Fragment-Based Test Generation For Web Apps
• Regularization Learning Networks: Deep Learning for Tabular Datasets
• Best arm identification in multi-armed bandits with delayed feedback
• Optimization, fast and slow: optimally switching between local and Bayesian optimization
• ZOOpt: Toolbox for Derivative-Free Optimization
• Sequential Model-Based Ensemble Optimization
• Multi-Fidelity Bayesian Optimization via Deep Neural Networks
• Model-based Asynchronous Hyperparameter and Neural Architecture Search
• Efficient Optimization of Echo State Networks for Time Series Datasets
• BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables
• Complex data labeling with deep learning methods: Lessons from fisheries acoustics
• MEMe: An Accurate Maximum Entropy Method for Efficient Approximations in Large-Scale Machine Learning
• Robust Federated Learning Through Representation Matching and Adaptive Hyper-parameters
• CODEBench: A Neural Architecture and Hardware Accelerator Co-Design Framework
• Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers
• A Programmable Approach to Neural Network Compression
• Automatic Document Image Binarization using Bayesian Optimization
• A Model to Search for Synthesizable Molecules
• Predictive intraday correlations in stable and volatile market environments: Evidence from deep learning
• Characterizing Bias in Classifiers using Generative Models
• Toward Drug-Target Interaction Prediction via Ensemble Modeling and Transfer Learning
• Benchmarking deep inverse models over time, and the neural-adjoint method
• Automated Machine Learning on Big Data using Stochastic Algorithm Tuning
• Structural Compression of Convolutional Neural Networks
• Model Inversion Networks for Model-Based Optimization
• Deep Learning at 15PF: Supervised and Semi-Supervised Classification for Scientific Data
• A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning
• Hyperparameter Learning via Distributional Transfer
• Data-Driven Methods to Monitor, Model, Forecast and Control Covid-19 Pandemic: Leveraging Data Science, Epidemiology and Control Theory
• Deep Complex Networks for Protocol-Agnostic Radio Frequency Device Fingerprinting in the Wild
• Using J-K fold Cross Validation to Reduce Variance When Tuning NLP Models
• Introducing an Explicit Symplectic Integration Scheme for Riemannian Manifold Hamiltonian Monte Carlo
• Sequential design of multi-fidelity computer experiments: maximizing the rate of stepwise uncertainty reduction
• Continual Learning in Practice
• Bayesian optimization for inverse problems in time-dependent quantum dynamics
• Identifying Bias in AI using Simulation
• Scalable Constrained Bayesian Optimization
• Optimization of the Shape of a Hydrokinetic Turbine's Draft Tube and Hub Assembly Using Design-by-Morphing with Bayesian Optimization
• Why Non-myopic Bayesian Optimization is Promising and How Far Should We Look-ahead? A Study via Rollout
• Numerical issues in maximum likelihood parameter estimation for Gaussian process interpolation
• How to Blend a Robot within a Group of Zebrafish: Achieving Social Acceptance through Real-time Calibration of a Multi-level Behavioural Model
• Neural Architecture Generator Optimization
• Meta-Learning for Stochastic Gradient MCMC
• Truncated Back-propagation for Bilevel Optimization
• Entity Personalized Talent Search Models with Tree Interaction Features
• Accelerating PDE-constrained Inverse Solutions with Deep Learning and Reduced Order Models
• BEHRT: Transformer for Electronic Health Records
• Using AntiPatterns to avoid MLOps Mistakes
• RIBBON: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instances
• Transfer Learning for the Efficient Detection of COVID-19 from Smartphone Audio Data
• Supervised machine learning to estimate instabilities in chaotic systems: estimation of local Lyapunov exponents
• Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
• Autofocused oracles for model-based design
• Zeroth-Order Algorithms for Nonconvex Minimax Problems with Improved Complexities
• Online regularization of complex-valued neural networks for structure optimization in wireless-communication channel prediction
• Suggesting Cooking Recipes Through Simulation and Bayesian Optimization
• Deep Collective Matrix Factorization for Augmented Multi-View Learning
• MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction
• Unbounded Bayesian Optimization via Regularization
• Hyperparameter Optimization and Boosting for Classifying Facial Expressions: How good can a "Null" Model be?
• Optimization Monte Carlo: Efficient and Embarrassingly Parallel Likelihood-Free Inference
• Multi-Objective Automatic Machine Learning with AutoxgboostMC
• Physics-Aware Multifidelity Bayesian Optimization: a Generalized Formulation
• Auto-Surprise: An Automated Recommender-System (AutoRecSys) Library with Tree of Parzens Estimator (TPE) Optimization
• What do you Mean? The Role of the Mean Function in Bayesian Optimisation
• Constant-Time Predictive Distributions for Gaussian Processes
• Adaptive Nonparametric Psychophysics
• The Gaussian Process Autoregressive Regression Model (GPAR)
• Learning Adaptive Loss for Robust Learning with Noisy Labels
• Bayesian Hyperparameter Optimization with BoTorch, GPyTorch and Ax
• Bayesian Optimization in a Billion Dimensions via Random Embeddings
• Parallel Architecture and Hyperparameter Search via Successive Halving and Classification
• A Probabilistic Machine Learning Approach to Scheduling Parallel Loops with Bayesian Optimization
• Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations
• Learning Directed Locomotion in Modular Robots with Evolvable Morphologies
• On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
• Mondrian Forests for Large-Scale Regression when Uncertainty Matters
• Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale
• Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces
• Using a thousand optimization tasks to learn hyperparameter search strategies
• Neural-BO: A Black-box Optimization Algorithm using Deep Neural Networks
• GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
• Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?
• Apollo: Transferable Architecture Exploration
• Finding safe 3D robot grasps through efficient haptic exploration with unscented Bayesian optimization and collision penalty
• Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization
• Deep Clustered Convolutional Kernels
• Machine learning classification of non-Markovian noise disturbing quantum dynamics
• TransBO: Hyperparameter Optimization via Two-Phase Transfer Learning
• Learnable Embedding Space for Efficient Neural Architecture Compression
• Bayesian optimization of hyper-parameters in reservoir computing
• Hyperparameter Optimization via Sequential Uniform Designs
• Learning Representations Using Complex-Valued Nets
• Inferring proximity from Bluetooth Low Energy RSSI with Unscented Kalman Smoothers
• Fast Efficient Hyperparameter Tuning for Policy Gradients
• A hierarchical expected improvement method for Bayesian optimization
• Big Learning with Bayesian Methods
• Intelligent Protection & Classification of Transients in Two-Core Symmetric Phase Angle Regulating Transformers
• Bayesian Optimisation over Multiple Continuous and Categorical Inputs
• Genetic Architect: Discovering Genomic Structure with Learned Neural Architectures
• Multi-level CNN for lung nodule classification with Gaussian Process assisted hyperparameter optimization
• Benchmarking the Neural Linear Model for Regression
• Convergence Guarantees for Gaussian Process Means With Misspecified Likelihoods and Smoothness
• Efficiently Sampling Functions from Gaussian Process Posteriors
• Designing Robust Biotechnological Processes Regarding Variabilities using Multi-Objective Optimization Applied to a Biopharmaceutical Seed Train Design
• Optimizing Prediction Intervals by Tuning Random Forest via Meta-Validation
• Leveraging Trust for Joint Multi-Objective and Multi-Fidelity Optimization
• A Gradient-based Bilevel Optimization Approach for Tuning Hyperparameters in Machine Learning
• A Unified Stochastic Gradient Approach to Designing Bayesian-Optimal Experiments
• HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization
• Nanophotonic Media for Artificial Neural Inference
• Accurate and efficient predictions of keyhole dynamics in laser materials processing using machine learning-aided simulations
• Fast Matrix Square Roots with Applications to Gaussian Processes and Bayesian Optimization
• Hybrid Parameter Search and Dynamic Model Selection for Mixed-Variable Bayesian Optimization
• Knowing The What But Not The Where in Bayesian Optimization
• Sequential Gaussian Processes for Online Learning of Nonstationary Functions
• Minimum Regret Search for Single- and Multi-Task Optimization
• Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
• PED-ANOVA: Efficiently Quantifying Hyperparameter Importance in Arbitrary Subspaces
• Time Efficiency in Optimization with a Bayesian-Evolutionary Algorithm
• Convolution Neural Network Hyperparameter Optimization Using Simplified Swarm Optimization
• A Novel Genetic Algorithm with Hierarchical Evaluation Strategy for Hyperparameter Optimisation of Graph Neural Networks
• Max-value Entropy Search for Multi-Objective Bayesian Optimization with Constraints
• Fast Task-Aware Architecture Inference
• Bayesian Optimisation for Active Monitoring of Air Pollution
• Meta-Learning surrogate models for sequential decision making
• HyperNOMAD: Hyperparameter optimization of deep neural networks using mesh adaptive direct search
• Exploration of new chemical materials using black-box optimization with the D-wave quantum annealer
• Evolutionary Neural AutoML for Deep Learning
• Combining Graph Neural Networks and Spatio-temporal Disease Models to Predict COVID-19 Cases in Germany
• Efficient force field and energy emulation through partition of permutationally equivalent atoms
• StructOpt: A modular materials structure optimization suite incorporating experimental data and simulated energies
• Neural Network Architecture Optimization through Submodularity and Supermodularity
• Better call Surrogates: A hybrid Evolutionary Algorithm for Hyperparameter optimization
• Rethinking Default Values: a Low Cost and Efficient Strategy to Define Hyperparameters
• Counterfactual Explanations for Arbitrary Regression Models
• TunaOil: A Tuning Algorithm Strategy for Reservoir Simulation Workloads
• A hyperparameter-tuning approach to automated inverse planning
• Faster variational quantum algorithms with quantum kernel-based surrogate models
• Neural Feature Learning From Relational Database
• Kernel Recursive ABC: Point Estimation with Intractable Likelihood
• Data acquisition and image processing for solar irradiance forecasting
• Hyperboost: Hyperparameter Optimization by Gradient Boosting surrogate models
• BayesFT: Bayesian Optimization for Fault Tolerant Neural Network Architecture
• client2vec: Towards Systematic Baselines for Banking Applications
• Exploiting correlation and budget constraints in Bayesian multi-armed bandit optimization
• Uncertainty in Multitask Transfer Learning
• An ADMM Based Framework for AutoML Pipeline Configuration
• Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization
• Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search
• Forecasting steam mass flow in power plants using the parallel hybrid network
• Optimizing Energy Management of Smart Grid using Reinforcement Learning aided by Surrogate models built using Physics-informed Neural Networks
• Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search
• Epsilon-Greedy Thompson Sampling to Bayesian Optimization
• Application of Deep Learning on Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations
• Batch simulations and uncertainty quantification in Gaussian process surrogate approximate Bayesian computation
• Metric Flows with Neural Networks
• Tuneful: An Online Significance-Aware Configuration Tuner for Big Data Analytics
• Parallel Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints
• Transfer Learning based Search Space Design for Hyperparameter Tuning
• Multi-objective Bayesian optimisation with preferences over objectives
• Online Hyper-parameter Learning for Auto-Augmentation Strategy
• Traversing the Reality Gap via Simulator Tuning
• HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO
• Optimizing with Low Budgets: a Comparison on the Black-box Optimization Benchmarking Suite and OpenAI Gym
• Searching to Exploit Memorization Effect in Learning from Corrupted Labels
• A One-Class Support Vector Machine Calibration Method for Time Series Change Point Detection
• Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians
• Multivariate, Multistep Forecasting, Reconstruction and Feature Selection of Ocean Waves via Recurrent and Sequence-to-Sequence Networks
• Reasoning about Hypothetical Agent Behaviours and their Parameters
• Scalable Combinatorial Bayesian Optimization with Tractable Statistical models
• Bayesian Optimization with Binary Auxiliary Information
• Scaling Gaussian Processes with Derivative Information Using Variational Inference
• Normalized Online Learning
• High-dimensional reinforcement learning for optimization and control of ultracold quantum gases
• Model Selection's Disparate Impact in Real-World Deep Learning Applications
• Optimal Data Generation in Multi-Dimensional Parameter Spaces, using Bayesian Optimization
• Smallify: Learning Network Size while Training
• Efficient Exploration in Binary and Preferential Bayesian Optimization
• Global Continuous Optimization with Error Bound and Fast Convergence
• PHOENICS: A universal deep Bayesian optimizer
• FLASH: Fast Bayesian Optimization for Data Analytic Pipelines
• Evaluation System for a Bayesian Optimization Service
• Corruption-Tolerant Gaussian Process Bandit Optimization
• Embarrassingly Parallel Inference for Gaussian Processes
• Learned Hardware/Software Co-Design of Neural Accelerators
• A Metaheuristic Approach for Mining Gradual Patterns
• Optimal Cost Design for Model Predictive Control
• Plasma Spray Process Parameters Configuration using Sample-efficient Batch Bayesian Optimization
• GIBBON: General-purpose Information-Based Bayesian OptimisatioN
• Bayesian Optimization for Selecting Efficient Machine Learning Models
• Non-separable Nearest-Neighbor Gaussian Process Model for Antarctic Surface Mass Balance and Ice Core Site Selection
• Solving Compositional Reinforcement Learning Problems via Task Reduction
• CADET: Debugging and Fixing Misconfigurations using Counterfactual Reasoning
• Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification
• Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation
• DeepAISE -- An End-to-End Development and Deployment of a Recurrent Neural Survival Model for Early Prediction of Sepsis
• Benchmarking time series classification -- Functional data vs machine learning approaches
• Decentralized Informative Path Planning with Exploration-Exploitation Balance for Swarm Robotic Search
• How Bayesian Should Bayesian Optimisation Be?
• Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret
• Hyper-parameter estimation method with particle swarm optimization
• uPredict: A User-Level Profiler-Based Predictive Framework for Single VM Applications in Multi-Tenant Clouds
• Towards Assessing the Impact of Bayesian Optimization's Own Hyperparameters
• On Information Gain and Regret Bounds in Gaussian Process Bandits
• AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification
• PANDA: Facilitating Usable AI Development
• Discrete Simulation Optimization for Tuning Machine Learning Method Hyperparameters
• A Comparative Analysis on Metaheuristic Algorithms Based Vision Transformer Model for Early Detection of Alzheimer's Disease
• Compromise-free Bayesian neural networks
• Probabilistic selection of inducing points in sparse Gaussian processes
• Combinatorial 3D Shape Generation via Sequential Assembly
• Surrogate Optimization of Deep Neural Networks for Groundwater Predictions
• Macaw: The Machine Learning Magnetometer Calibration Workflow
• Deep neural network initialization with decision trees
• Residual Squeeze VGG16
• Deep Multi-Fidelity Active Learning of High-dimensional Outputs
• Reproducible Performance Optimization of Complex Applications on the Edge-to-Cloud Continuum
• MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning
• A Linear Programming Enhanced Genetic Algorithm for Hyperparameter Tuning in Machine Learning
• Lifelong Bayesian Optimization
• Reinforcement Learning Informed Evolutionary Search for Autonomous Systems Testing
• Low Emission Building Control with Zero-Shot Reinforcement Learning
• AQEyes: Visual Analytics for Anomaly Detection and Examination of Air Quality Data
• From Maxout to Channel-Out: Encoding Information on Sparse Pathways
• Compiler-Level Matrix Multiplication Optimization for Deep Learning
• Adaptive Gaussian process surrogates for Bayesian inference
• A Transfer Learning-based State of Charge Estimation for Lithium-Ion Battery at Varying Ambient Temperatures
• Semi-supervised Embedding Learning for High-dimensional Bayesian Optimization
• AutoML to Date and Beyond: Challenges and Opportunities
• Sampling Acquisition Functions for Batch Bayesian Optimization
• Recognition of food-texture attributes using an in-ear microphone
• Learning Strict Identity Mappings in Deep Residual Networks
• Hidden Incentives for Auto-Induced Distributional Shift
• Meta-Surrogate Benchmarking for Hyperparameter Optimization
• A Nonparametric Unsupervised Learning Approach for Structural Damage Detection
• Bayesian Optimization of 2D Echocardiography Segmentation
• Budgeted Batch Bayesian Optimization With Unknown Batch Sizes
• NeuNetS: An Automated Synthesis Engine for Neural Network Design
• Latent Model Ensemble with Auto-localization
• Meta-Learning Initializations for Image Segmentation
• DeepOBS: A Deep Learning Optimizer Benchmark Suite
• Bayesian Optimization with Dimension Scheduling: Application to Biological Systems
• Non-Myopic Multifidelity Bayesian Optimization
• Bayesian Optimized Continual Learning with Attention Mechanism
• Parallel optimization for large eddy simulations
• An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models
• Two-step hyperparameter optimization method: Accelerating hyperparameter search by using a fraction of a training dataset
• Multi-Step Budgeted Bayesian Optimization with Unknown Evaluation Costs
• Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels
• Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces
• Facilitating Database Tuning with Hyper-Parameter Optimization: A Comprehensive Experimental Evaluation
• Movie rating prediction using content-based and link stream features
• Evolution under Length Constraints for CNN Architecture design
• AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly
• NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
• Solving Black-Box Optimization Challenge via Learning Search Space Partition for Local Bayesian Optimization
• Training Stronger Baselines for Learning to Optimize
• Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
• A Principled Approach to Design Using High Fidelity Fluid-Structure Interaction Simulations
• An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization
• Uncertainty quantification using martingales for misspecified Gaussian processes
• Optimal Order Simple Regret for Gaussian Process Bandits
• Pareto-efficient Acquisition Functions for Cost-Aware Bayesian Optimization
• Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
• Exploiting the Statistics of Learning and Inference
• Transferable Neural Processes for Hyperparameter Optimization
• A Generalized Framework for Population Based Training
• Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation
• Efficient Online Hyperparameter Optimization for Kernel Ridge Regression with Applications to Traffic Time Series Prediction
• Deep Ensembles on a Fixed Memory Budget: One Wide Network or Several Thinner Ones?
• Graph Bayesian Optimization: Algorithms, Evaluations and Applications
• MLtuner: System Support for Automatic Machine Learning Tuning
• Adaptive and Resilient Soft Tensegrity Robots
• Incorporating Expert Prior Knowledge into Experimental Design via Posterior Sampling
• Regularization Path of Cross-Validation Error Lower Bounds
• Learning Effective Loss Functions Efficiently
• No more meta-parameter tuning in unsupervised sparse feature learning
• Active Contextual Entropy Search
• Designing Adaptive Neural Networks for Energy-Constrained Image Classification
• Probabilistic Programming with Gaussian Process Memoization
• HyperSTAR: Task-Aware Hyperparameters for Deep Networks
• Rethinking Performance Estimation in Neural Architecture Search
• Sample-Efficient Automated Deep Reinforcement Learning
• AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning
• Pathwise Conditioning of Gaussian Processes
• Analyzing the Effectiveness of Quantum Annealing with Meta-Learning
• Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior
• Mood Classification Using Listening Data
• Black Box Submodular Maximization: Discrete and Continuous Settings
• Learning Personalized Thermal Preferences via Bayesian Active Learning with Unimodality Constraints
• Exploiting Reuse in Pipeline-Aware Hyperparameter Tuning
• Faster Improvement Rate Population Based Training
• Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting
• Justification-Based Reliability in Machine Learning
• Quantifying contribution and propagation of error from computational steps, algorithms and hyperparameter choices in image classification pipelines
• Diversified Sampling for Batched Bayesian Optimization with Determinantal Point Processes
• Computationally Efficient High-Dimensional Bayesian Optimization via Variable Selection
• Read, Tag, and Parse All at Once, or Fully-neural Dependency Parsing
• Gaussian process modeling in approximate Bayesian computation to estimate horizontal gene transfer in bacteria
• A Learning-Based Tune-Free Control Framework for Large Scale Autonomous Driving System Deployment
• Learning to Compare for Better Training and Evaluation of Open Domain Natural Language Generation Models
• Adaptive Rate of Convergence of Thompson Sampling for Gaussian Process Optimization
• Persistent Homology for Structural Characterization in Disordered Systems
• Information-Guided Sampling for Low-Rank Matrix Completion
• Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation
• Identifying Model Weakness with Adversarial Examiner
• Genetic Neural Architecture Search for automatic assessment of human sperm images
• JITuNE: Just-In-Time Hyperparameter Tuning for Network Embedding Algorithms
• Two network Kuramoto-Sakaguchi model under tempered stable Lévy noise
• No-regret Algorithms for Multi-task Bayesian Optimization
• Scalable Thompson Sampling using Sparse Gaussian Process Models
• Multitask and Transfer Learning for Autotuning Exascale Applications
• HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
• Quantity vs. Quality: On Hyperparameter Optimization for Deep Reinforcement Learning
• Controlling Biofilm Transport with Porous Metamaterials Designed with Bayesian Learning
• Semi-Supervised Learning with Declaratively Specified Entropy Constraints
• Distributed Training and Optimization Of Neural Networks
• The Nonlinearity Coefficient - A Practical Guide to Neural Architecture Design
• BOSH: Bayesian Optimization by Sampling Hierarchically
• Tune smarter not harder: A principled approach to tuning learning rates for shallow nets
• Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm
• Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Tasks
• Towards White-box Benchmarks for Algorithm Control
• Efficient AutoML Pipeline Search with Matrix and Tensor Factorization
• Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL
• Discriminative Nonparametric Latent Feature Relational Models with Data Augmentation
• Learning to guide task and motion planning using score-space representation
• Adaptive Local Bayesian Optimization Over Multiple Discrete Variables
• Removing Class Imbalance using Polarity-GAN: An Uncertainty Sampling Approach
• Adaptive Bayesian Linear Regression for Automated Machine Learning
• Active learning based generative design for the discovery of wide bandgap materials
• Bayesian Neural Networks for Virtual Flow Metering: An Empirical Study
• A Deep Learning Application for Psoriasis Detection
• Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning
• Open Loop Hyperparameter Optimization and Determinantal Point Processes
• Real-Time Boiler Control Optimization with Machine Learning
• A Scalable Gradient-Free Method for Bayesian Experimental Design with Implicit Models
• Practical Bayesian Optimization for Transportation Simulators
• A gray-box approach for curriculum learning
• Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees
• Practical Batch Bayesian Optimization for Less Expensive Functions
• Optimizing Photonic Nanostructures via Multi-fidelity Gaussian Processes
• Lecture Notes: Optimization for Machine Learning
• AutoPilot: Automating SoC Design Space Exploration for SWaP Constrained Autonomous UAVs
• Experimental Standards for Deep Learning in Natural Language Processing Research
• A Genetic Algorithm with Tree-structured Mutation for Hyperparameter Optimisation of Graph Neural Networks
• Regularized deep learning with nonconvex penalties
• BISTRO: Berkeley Integrated System for Transportation Optimization
• Bayesian Optimization for Iterative Learning
• New Hybrid Neuro-Evolutionary Algorithms for Renewable Energy and Facilities Management Problems
• Deep-n-Cheap: An Automated Search Framework for Low Complexity Deep Learning
• Optimizing Discrete Spaces via Expensive Evaluations: A Learning to Search Framework
• BINOCULARS for Efficient, Nonmyopic Sequential Experimental Design
• Online Hyperparameter Meta-Learning with Hypergradient Distillation
• Learned Indexes for Dynamic Workloads
• Neural Semantic Role Labeling with Dependency Path Embeddings
• Automatic model training under restrictive time constraints
• Hyper-parameter Tuning under a Budget Constraint
• Non-smooth Bayesian Optimization in Tuning Problems
• Practical Transfer Learning for Bayesian Optimization
• Recognizing Intent in Collaborative Manipulation
• Early Diagnosis of Retinal Blood Vessel Damage via Deep Learning-Powered Collective Intelligence Models
• No-Regret Bayesian Optimization with Unknown Hyperparameters
• Meaning to Form: Measuring Systematicity as Information
• On the role of Model Uncertainties in Bayesian Optimization
• Gauss-Legendre Features for Gaussian Process Regression
• On the development of a practical Bayesian optimisation algorithm for expensive experiments and simulations with changing environmental conditions
• Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning
• Augmenting and Tuning Knowledge Graph Embeddings
• Augmentation of the Electron Counting Rule with Ising Model
• Learning Correlation Space for Time Series
• Regularized Evolutionary Population-Based Training
• Multi-Step Bayesian Optimization for One-Dimensional Feasibility Determination
• Bank Card Usage Prediction Exploiting Geolocation Information
• Quantum transfer through small networks coupled to phonons: effects of topology vs phonons
• Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties
• Stochastic Weight Matrix-based Regularization Methods for Deep Neural Networks
• Good practices for Bayesian Optimization of high dimensional structured spaces
• Hyperparameter optimization with REINFORCE and Transformers
• Efficient Transfer Bayesian Optimization with Auxiliary Information
• Surrogate-based Optimization using Mutual Information for Computer Experiments (optim-MICE)
• Understanding ML driven HPC: Applications and Infrastructure
• Online hyperparameter optimization by real-time recurrent learning
• Sparse Spectrum Gaussian Process for Bayesian Optimization
• BORE: Bayesian Optimization by Density-Ratio Estimation
• Bayesian Optimization with Approximate Set Kernels
• Efficient Batch Black-box Optimization with Deterministic Regret Bounds
• No-Regret Algorithms for Private Gaussian Process Bandit Optimization
• Hyperparameter Transfer Learning with Adaptive Complexity
• Attentive Neural Processes and Batch Bayesian Optimization for Scalable Calibration of Physics-Informed Digital Twins
• Implicit Feedback Deep Collaborative Filtering Product Recommendation System
• Problem-fluent models for complex decision-making in autonomous materials research
• A Sensitivity-based Data Augmentation Framework for Model Predictive Control Policy Approximation
• A Nonmyopic Approach to Cost-Constrained Bayesian Optimization
• Scalable Acceleration for Classification-Based Derivative-Free Optimization
• Hyperparameter Transfer Across Developer Adjustments
• Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization
• Noisy Blackbox Optimization with Multi-Fidelity Queries: A Tree Search Approach
• A Scalable and Cloud-Native Hyperparameter Tuning System
• Hippo: Taming Hyper-parameter Optimization of Deep Learning with Stage Trees
• Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks
• Stability and Generalization of Bilevel Programming in Hyperparameter Optimization
• Neural Generative Models for Global Optimization with Gradients
• Solving Constrained CASH Problems with ADMM
• Scalable Gaussian Process Inference with Finite-data Mean and Variance Guarantees
• AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling
• Multi-level Training and Bayesian Optimization for Economical Hyperparameter Optimization
• Selecting Data Adaptive Learner from Multiple Deep Learners using Bayesian Networks
• Using Distance Correlation for Efficient Bayesian Optimization
• BoGraph: Structured Bayesian Optimization From Logs for Expensive Systems with Many Parameters
• FedGPO: Heterogeneity-Aware Global Parameter Optimization for Efficient Federated Learning
• Hierarchical Proxy-based Loss for Deep Metric Learning
• Neural Model-based Optimization with Right-Censored Observations
• Autotuning PolyBench Benchmarks with LLVM Clang/Polly Loop Optimization Pragmas Using Bayesian Optimization (extended version)
• Go with the Flow: Perception-refined Physics Simulation
• Machine-learned metrics for predicting the likelihood of success in materials discovery
• Reinforcement Learning To Adapt Speech Enhancement to Instantaneous Input Signal Quality
• BERT for Large-scale Video Segment Classification with Test-time Augmentation
• Pseudo-Encoded Stochastic Variational Inference
• Information Geometrically Generalized Covariate Shift Adaptation
• CNN-LSTM models for Multi-Speaker Source Separation using Bayesian Hyper Parameter Optimization
• Feature selection in machine learning: Rényi min-entropy vs Shannon entropy
• Multi-Task Multicriteria Hyperparameter Optimization
• Domain Knowledge Injection in Bayesian Search for New Materials
• Considerations for optimizing photometric classification of supernovae from the Rubin Observatory
• Data-Driven Offline Optimization For Architecting Hardware Accelerators
• Gaussian Process Bandit Optimization with Few Batches
• Constrained Discrete Black-Box Optimization using Mixed-Integer Programming
• ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies
• A General Framework for Constrained Bayesian Optimization using Information-based Search
• Super-resolution of Time-series Labels for Bootstrapped Event Detection
• Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework
• Imbalanced Regression Pipeline Recommendation
• Regional medical inter-institutional cooperation in medical provider network constructed using patient claims data from Japan
• RoMA: Robust Model Adaptation for Offline Model-based Optimization
• Time-varying Gaussian Process Bandit Optimization with Non-constant Evaluation Time
• Optimizing Bayesian acquisition functions in Gaussian Processes
• Bayesian Optimization in Materials Science: A Survey
• Privacy-Preserving Record Linkage
• Automated Hyperparameter Optimization Challenge at CIKM 2021 AnalyticCup
• Gradient-only line searches to automatically determine learning rates for a variety of stochastic training algorithms
• Funneled Bayesian Optimization for Design, Tuning and Control of Autonomous Systems
• The Renyi Gaussian Process: Towards Improved Generalization
• Classification of Human Whole-Body Motion using Hidden Markov Models
• BO-DBA: Query-Efficient Decision-Based Adversarial Attacks via Bayesian Optimization
• Comparing methods addressing multi-collinearity when developing prediction models
• Fine-Grained Classroom Activity Detection from Audio with Neural Networks
• Parameter-Based Value Functions
• Optimizing Recurrent Neural Networks Architectures under Time Constraints
• RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels
• Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization
• End-to-End Learning of Deep Kernel Acquisition Functions for Bayesian Optimization
• Online Optimization of Stimulation Speed in an Auditory Brain-Computer Interface under Time Constraints
• Trust-Region Algorithms for Training Responses: Machine Learning Methods Using Indefinite Hessian Approximations
• Bayesian optimization with local search
• Gradient Regularized Budgeted Boosting
• Preferential Batch Bayesian Optimization
• Optimizing for Generalization in Machine Learning with Cross-Validation Gradients
• Adaptive Pricing in Insurance: Generalized Linear Models and Gaussian Process Regression Approaches
• Which Surrogate Works for Empirical Performance Modelling? A Case Study with Differential Evolution
• Parameter Optimization for Loop Closure Detection in Closed Environments
• Interactive Text Ranking with Bayesian Optimisation: A Case Study on Community QA and Summarisation
• A Similarity Measure of Gaussian Process Predictive Distributions
• Analyzing high-dimensional time-series data using kernel transfer operator eigenfunctions
• ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale
• Speed-Constrained Tuning for Statistical Machine Translation Using Bayesian Optimization
• Image-Based Jet Analysis
• High Dimensional Level Set Estimation with Bayesian Neural Network
• Sparse representation for damage identification of structural systems
• Trusted-Maximizers Entropy Search for Efficient Bayesian Optimization
• How Likely are Ride-share Drivers to Earn a Living Wage? Large-scale Spatio-temporal Density Smoothing with the Graph-fused Elastic Net
• Learning Optimal Linear Regularizers
• On Hyper-parameter Tuning for Stochastic Optimization Algorithms
• Gaussian Process Boosting
• Adversarial Attacks on Gaussian Process Bandits
• Gaussian Process Sampling and Optimization with Approximate Upper and Lower Bounds
• ExperienceThinking: Constrained Hyperparameter Optimization based on Knowledge and Pruning
• A Simple Heuristic for Bayesian Optimization with A Low Budget
• Progressive Learning Algorithm for Efficient Person Re-Identification
• An Earth-System-Oriented View of the S2S Predictability of North American Weather Regimes
• Bayesian optimization of non-classical optomechanical correlations
• Contact Map based Crystal Structure Prediction using Global Optimization
• Constructing trading strategy ensembles by classifying market states
• Reducing The Search Space For Hyperparameter Optimization Using Group Sparsity
• Scale estimation and rate-unbiasedness for Gaussian processes under smoothness misspecification
• Sampling Humans for Optimizing Preferences in Coloring Artwork
• Statistical Inference for Polyak-Ruppert Averaged Zeroth-order Stochastic Gradient Algorithm
• Advanced Machine Learning Framework for Efficient Plant Disease Prediction
• Detection and classification of vocal productions in large scale audio recordings
• Contextual Bayesian optimization with binary outputs
• Gaussian Process Inference Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits
• Mixed Variable Bayesian Optimization with Frequency Modulated Kernels
• QROSS: QUBO Relaxation Parameter Optimisation via Learning Solver Surrogates
• Simple and Efficient Hard Label Black-box Adversarial Attacks in Low Query Budget Regimes
• Learning Locomotion Skills in Evolvable Robots
• Training Deep Neural Networks by optimizing over nonlocal paths in hyperparameter space
• Scalable Multi-Class Bayesian Support Vector Machines for Structured and Unstructured Data
• Generalized State-Feedback Controller Synthesis for Underactuated Systems through Bayesian Optimization
• Affinity-Based Hierarchical Learning of Dependent Concepts for Human Activity Recognition
• Efficient and Robust Machine Learning for Real-World Systems
• Learning Representations of Social Media Users
• Discovering Diverse Athletic Jumping Strategies
• Geometric Graph Representations and Geometric Graph Convolutions for Deep Learning on Three-Dimensional (3D) Graphs
• Adjoint-based trailing edge shape optimization of a transonic turbine vane using large eddy simulations
• Towards the Development of Entropy-Based Anomaly Detection in an Astrophysics Simulation
• On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms
• Muddling Labels for Regularization, a novel approach to generalization
• Utilizing remote sensing data in forest inventory sampling via Bayesian optimization
• Substitute Teacher Networks: Learning with Almost No Supervision
• Active Learning over DNN: Automated Engineering Design Optimization for Fluid Dynamics Based on Self-Simulated Dataset
• Meta-Learning for Symbolic Hyperparameter Defaults
• Mise en abyme with artificial intelligence: how to predict the accuracy of NN, applied to hyper-parameter tuning
• The unified maximum a posteriori (MAP) framework for neuronal system identification
• MBORE: Multi-objective Bayesian Optimisation by Density-Ratio Estimation
• Implicit Differentiation for Hyperparameter Tuning the Weighted Graphical Lasso
• Auto-Model: Utilizing Research Papers and HPO Techniques to Deal with the CASH problem
• Efficient Rollout Strategies for Bayesian Optimization
• Practical Bayesian Optimization of Objectives with Conditioning Variables
• Optimization for Gaussian Processes via Chaining
• Financial Data Analysis Using Expert Bayesian Framework For Bankruptcy Prediction
• A Markov Jump Process for More Efficient Hamiltonian Monte Carlo
• LAMVI-2: A Visual Tool for Comparing and Tuning Word Embedding Models
• A Simple Way to Deal with Cherry-picking
• Tuning for Tissue Image Segmentation Workflows for Accuracy and Performance
• Towards QoS-Aware and Resource-Efficient GPU Microservices Based on Spatial Multitasking GPUs In Datacenters
• Constrained, Global Optimization of Functions with Lipschitz Continuous Gradients
• Automated Machine Learning, Bounded Rationality, and Rational Metareasoning
• PURS: Personalized Unexpected Recommender System for Improving User Satisfaction
• Designing MacPherson Suspension Architectures using Bayesian Optimization
• Efficient Bayesian Optimization using Multiscale Graph Correlation
• Efficient Model Performance Estimation via Feature Histories
• Efficient Phase Diagram Sampling by Active Learning
• MISO-wiLDCosts: Multi Information Source Optimization with Location Dependent Costs
• Privileged Zero-Shot AutoML
• Stabilizing Bi-Level Hyperparameter Optimization using Moreau-Yosida Regularization
• AutoCP: Automated Pipelines for Accurate Prediction Intervals
• Toward Verifiable Real-Time Obstacle Motion Prediction for Dynamic Collision Avoidance
• Global Optimisation of Black-Box Functions with Generative Models in the Wasserstein Space
• Can a powerful neural network be a teacher for a weaker neural network?
• Learning How to Optimize Black-Box Functions With Extreme Limits on the Number of Function Evaluations
• Bayesian optimization assisted unsupervised learning for efficient intra-tumor partitioning in MRI and survival prediction for glioblastoma patients
• Parameterless Stochastic Natural Gradient Method for Discrete Optimization and its Application to Hyper-Parameter Optimization for Neural Network
• New Heuristics for Parallel and Scalable Bayesian Optimization
• Practical Bayesian Optimization with Threshold-Guided Marginal Likelihood Maximization
• Forecasting Daily COVID-19 Related Calls in VA Health Care System: Predictive Model Development
• Cross-Correlation Based Discriminant Criterion for Channel Selection in Motor Imagery BCI Systems
• Simple and Scalable Parallelized Bayesian Optimization
• MTAdam: Automatic Balancing of Multiple Training Loss Terms
• Black Box Probabilistic Numerics
• Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling
• Auto-CASH: Autonomous Classification Algorithm Selection with Deep Q-Network
• No Regret Bound for Extreme Bandits
• Nonmyopic Multifidelity Active Search
• Ply-drop design of non-conventional composites using Bayesian optimization
• Predicting the success of Gradient Descent for a particular Dataset-Architecture-Initialization (DAI)
• Latent Unexpected Recommendations
• Bayesian Optimization for Developmental Robotics with Meta-Learning by Parameters Bounds Reduction
• REflex: Flexible Framework for Relation Extraction in Multiple Domains
• Hyper-optimization with Gaussian Process and Differential Evolution Algorithm
• Accelerated Bayesian Optimization throughWeight-Prior Tuning
• Efficient Hyperparameter Optimization for Differentially Private Deep Learning
• Bayesian optimization for modular black-box systems with switching costs
• A tree-based radial basis function method for noisy parallel surrogate optimization
• Fusing heterogeneous data sets
• A Data-Driven Approach for Predicting Hydrodynamic Forces on Spherical Particles Using Volume Fraction Representations
• Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations
• Optimal Use of Multi-spectral Satellite Data with Convolutional Neural Networks
• Identification of state functions by physically-guided neural networks with physically-meaningful internal layers
• fMRI Multiple Missing Values Imputation Regularized by a Recurrent Denoiser
• Tetra-AML: Automatic Machine Learning via Tensor Networks
• A Framework for Model Search Across Multiple Machine Learning Implementations
• PipeTune: Pipeline Parallelism of Hyper and System Parameters Tuning for Deep Learning Clusters
• A Dimension-Insensitive Algorithm for Stochastic Zeroth-Order Optimization
• One-parameter family of acquisition functions for efficient global optimization
• BOSH: An Efficient Meta Algorithm for Decision-based Attacks
• Multi-Stage Network Embedding for Exploring Heterogeneous Edges
• Surrogate Model Based Hyperparameter Tuning for Deep Learning with SPOT
• Cost-Efficient Online Hyperparameter Optimization
• Evolution of Scikit-Learn Pipelines with Dynamic Structured Grammatical Evolution
• Toward Optimal Run Racing: Application to Deep Learning Calibration
• Learning Arbitrary Quantities of Interest from Expensive Black-Box Functions through Bayesian Sequential Optimal Design
• Feature-wise change detection and robust indoor positioning using RANSAC-like approach
• Efficient Automatic Meta Optimization Search for Few-Shot Learning
• Quantifying the effect of representations on task complexity
• Machine Learning for Quantum Dynamics: Deep Learning of Excitation Energy Transfer Properties
• An Algorithmic Framework for Computing Validation Performance Bounds by Using Suboptimal Models
• Estimating Shape Parameters of Piecewise Linear-Quadratic Problems
• Tuning the Scheduling of Distributed Stochastic Gradient Descent with Bayesian Optimization
• AutoSmart: An Efficient and Automatic Machine Learning framework for Temporal Relational Data
• Bayesian task embedding for few-shot Bayesian optimization
• Scalable Hyperparameter Optimization with Lazy Gaussian Processes
• BayesOpt: A Library for Bayesian optimization with Robotics Applications
• Large-Scale Sleep Condition Analysis Using Selfies from Social Media
• A Review on Oracle Issues in Machine Learning
• Online Preconditioning of Experimental Inkjet Hardware by Bayesian Optimization in Loop
• Bayesian optimization for backpropagation in Monte-Carlo tree search
• Hyperparameter Optimization for Forecasting Stock Returns
• One dimensional consensus based algorithm for non-convex optimization
• Adaptive Simulation-based Training of AI Decision-makers using Bayesian Optimization
• Scalable Projection-Free Optimization
• Black-box Optimizer with Implicit Natural Gradient
• Online Parameter Estimation for Safety-Critical Systems with Gaussian Processes
• GaDei: On Scale-up Training As A Service For Deep Learning
• Active Offline Policy Selection
• Designing over uncertain outcomes with stochastic sampling Bayesian optimization
• Deep Bregman Divergence for Contrastive Learning of Visual Representations
• Evaluation Function Approximation for Scrabble
• Neural Architecture Search for Sentence Classification with BERT
• Matching with Transformers in MELT
• Adjoint-based Gradient Estimation Using the Space-time Solutions of Unknown Conservation Law Simulations
• Meta-Learning Conjugate Priors for Few-Shot Bayesian Optimization
• KnowMAN: Weakly Supervised Multinomial Adversarial Networks
• A Probabilistic Adaptive Search System for Exploring the Face Space
• Meta-Learning to Improve Pre-Training
• BOAssembler: a Bayesian Optimization Framework to Improve RNA-Seq Assembly Performance
• Black-Box Optimization of Object Detector Scales
• Robust Policy Search for Robot Navigation
• Shakeout: A New Approach to Regularized Deep Neural Network Training
• DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks
• Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation
• TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data
• Scaling Bayesian Optimization With Game Theory
• Long Short Term Memory Networks for Bandwidth Forecasting in Mobile Broadband Networks under Mobility
• Machine Learning Approach for Device-Circuit Co-Optimization of Stochastic-Memristive-Device-Based Boltzmann Machine
• DEEP-BO for Hyperparameter Optimization of Deep Networks
• Topological Data Analysis (TDA) Techniques Enhance Hand Pose Classification from ECoG Neural Recordings
• Autotuning PolyBench Benchmarks with LLVM Clang/Polly Loop Optimization Pragmas Using Bayesian Optimization
• A hybrid analytical-numerical algorithm for determining the neuronal current via EEG
• Bayesian Optimisation with Formal Guarantees
• ChaCha for Online AutoML
• Layer Flexible Adaptive Computational Time
• Concavifiability and convergence: necessary and sufficient conditions for gradient descent analysis
• Deep Bayesian Optimization on Attributed Graphs
• Efficient Hyperparameter Optimization for Physics-based Character Animation
• Doubly Bayesian Optimization
• Automatic low-bit hybrid quantization of neural networks through meta learning
• Prediction Factory: automated development and collaborative evaluation of predictive models
• Data-driven Predictive Energy Optimization in a Wastewater Pumping Station
• A Hybrid Monte Carlo Architecture for Parameter Optimization
• Probabilistic Predictions of People Perusing: Evaluating Metrics of Language Model Performance for Psycholinguistic Modeling
• Scalable Bayesian Optimization with Sparse Gaussian Process Models
• Using Known Information to Accelerate HyperParameters Optimization Based on SMBO