Stochastic Backpropagation and Approximate Inference in Deep Generative Models

Abstract

We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a recognition model to represent approximate posterior distributions, and that acts as a stochastic encoder of the data. We develop stochastic back-propagation -- rules for back-propagation through stochastic variables -- and use this to develop an algorithm that allows for joint optimisation of the parameters of both the generative and recognition model. We demonstrate on several real-world data sets that the model generates realistic samples, provides accurate imputations of missing data and is a useful tool for high-dimensional data visualisation.

Appears In Proceedings of the 31st International Conference on Machine Learning (ICML), JMLR: W\&CP volume 32, 2014

References in corpus (1)

• Stochastic Variational Inference

Cited by in corpus (852)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• A Brief Survey of Deep Reinforcement Learning
• Variational Inference: A Review for Statisticians
• Bootstrap your own latent: A new approach to self-supervised Learning
• An Introduction to Variational Autoencoders
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• NICE: Non-linear Independent Components Estimation
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Weight Uncertainty in Neural Networks
• Deep Learning for Single Image Super-Resolution: A Brief Review
• DRAW: A Recurrent Neural Network For Image Generation
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• Variational Graph Auto-Encoders
• Density estimation using Real NVP
• Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
• Adversarially Learned Inference
• Autoencoding beyond pixels using a learned similarity metric
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics
• Invertible Conditional GANs for image editing
• Semi-Supervised Learning with Generative Adversarial Networks
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• MolGAN: An implicit generative model for small molecular graphs
• Scalable Bayesian Optimization Using Deep Neural Networks
• Energy-based Out-of-distribution Detection
• Recent Advances in Autoencoder-Based Representation Learning
• InfoVAE: Information Maximizing Variational Autoencoders
• Large-Scale Study of Curiosity-Driven Learning
• A Survey of Sound Source Localization with Deep Learning Methods
• Count-Based Exploration with Neural Density Models
• Bayesian Compression for Deep Learning
• Variational Dropout Sparsifies Deep Neural Networks
• Differentially Private Generative Adversarial Network
• State Representation Learning for Control: An Overview
• GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
• Causal Effect Inference with Deep Latent-Variable Models
• Off-Policy Deep Reinforcement Learning without Exploration
• Graph networks as learnable physics engines for inference and control
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Auxiliary Deep Generative Models
• Learning by Playing - Solving Sparse Reward Tasks from Scratch
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Ladder Variational Autoencoders
• An Overview of Deep Semi-Supervised Learning
• Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
• Syntax-Directed Variational Autoencoder for Structured Data
• Multi-Object Representation Learning with Iterative Variational Inference
• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Triple Generative Adversarial Nets
• Video Compression With Rate-Distortion Autoencoders
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• Composing graphical models with neural networks for structured representations and fast inference
• Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
• Discovering Discrete Latent Topics with Neural Variational Inference
• Learning What and Where to Draw
• Stabilizing Training of Generative Adversarial Networks through Regularization
• Masked Autoregressive Flow for Density Estimation
• A Deep Reinforcement Learning Chatbot
• Disentangled Representation Learning in Cardiac Image Analysis
• Learning Stochastic Recurrent Networks
• Automatic Differentiation Variational Inference
• MONet: Unsupervised Scene Decomposition and Representation
• Variational Encoding of Complex Dynamics
• Improving Variational Inference with Inverse Autoregressive Flow
• Gradient Estimation Using Stochastic Computation Graphs
• MR image reconstruction using deep density priors
• Dynamical Variational Autoencoders: A Comprehensive Review
• Model-Free Episodic Control
• Gravitational-wave parameter estimation with autoregressive neural network flows
• Dynamic Word Embeddings
• Variational Recurrent Auto-Encoders
• A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Deep Learning and Model Predictive Control for Self-Tuning Mode-Locked Lasers
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
• Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
• Learning Sparse Neural Networks through $L_0$ Regularization
• Towards a Neural Statistician
• Variational inference for Monte Carlo objectives
• Classification Accuracy Score for Conditional Generative Models
• Isolating Sources of Disentanglement in Variational Autoencoders
• Deep Kalman Filters
• Scalable Gradients for Stochastic Differential Equations
• Dream to Control: Learning Behaviors by Latent Imagination
• Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
• TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis
• Deep Learning: A Bayesian Perspective
• Compressing Neural Networks using the Variational Information Bottleneck
• Variational Autoencoders and Nonlinear ICA: A Unifying Framework
• Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
• Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities
• How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
• BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
• A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
• Grammar Variational Autoencoder
• Sylvester Normalizing Flows for Variational Inference
• Black box variational inference for state space models
• Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification
• Lifelong Generative Modeling
• Stochastic Gradient Descent as Approximate Bayesian Inference
• Generating Diverse High-Fidelity Images with VQ-VAE-2
• From Variational to Deterministic Autoencoders
• Learning and Transfer of Modulated Locomotor Controllers
• Hyperspherical Variational Auto-Encoders
• Denoising Diffusion Implicit Models
• Time Series Diffusion Method: A Denoising Diffusion Probabilistic Model for Vibration Signal Generation
• Learning Disentangled Representations in the Imaging Domain
• Conditional Variational Image Deraining
• Machine learning with neural networks
• ODE${}^2$VAE: Deep generative second order ODEs with Bayesian neural networks
• Deep Variational Canonical Correlation Analysis
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• Unsupervised Learning of 3D Structure from Images
• Attribute2Image: Conditional Image Generation from Visual Attributes
• Connecting Generative Adversarial Networks and Actor-Critic Methods
• Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
• Improved Variational Autoencoders for Text Modeling using Dilated Convolutions
• Neural Episodic Control
• Loss is its own Reward: Self-Supervision for Reinforcement Learning
• TREND: TempoRal Event and Node Dynamics for Graph Representation Learning
• DIVA: Domain Invariant Variational Autoencoders
• D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
• Super-Resolution with Deep Convolutional Sufficient Statistics
• Data-Driven Design-by-Analogy: State of the Art and Future Directions
• Deep Probabilistic Programming
• Random Feature Expansions for Deep Gaussian Processes
• Improving Variational Auto-Encoders using Householder Flow
• Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection
• Unsupervised machine learning of topological phase transitions from experimental data
• Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
• Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI
• Inference Suboptimality in Variational Autoencoders
• Deep Survival Analysis
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider
• A-NICE-MC: Adversarial Training for MCMC
• Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
• Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
• DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
• Semi-supervised Deep Generative Modelling of Incomplete Multi-Modality Emotional Data
• LFADS - Latent Factor Analysis via Dynamical Systems
• Structured Pruning of a BERT-based Question Answering Model
• Contrastive Learning of Structured World Models
• Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
• Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder
• Deep learning for presumed probability density function models
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• CLVSA: A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets
• Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
• Machine Theory of Mind
• Low-Shot Learning from Imaginary Data
• Training Data Influence Analysis and Estimation: A Survey
• Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
• Variational Autoencoders for Collaborative Filtering
• Implicit Weight Uncertainty in Neural Networks
• Robust Imitation of Diverse Behaviors
• Variational Auto-encoded Deep Gaussian Processes
• Intriguing Properties of Contrastive Losses
• Lifelong Teacher-Student Network Learning
• Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertainty
• On denoising autoencoders trained to minimise binary cross-entropy
• Adversarial Images for Variational Autoencoders
• Improving Outfit Recommendation with Co-supervision of Fashion Generation
• Classification Aware Neural Topic Model and its Application on a New COVID-19 Disinformation Corpus
• Planning to Explore via Self-Supervised World Models
• Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training
• Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization
• Learning and Querying Fast Generative Models for Reinforcement Learning
• Pathwise Derivatives Beyond the Reparameterization Trick
• CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
• Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
• Learning Disentangled Joint Continuous and Discrete Representations
• Variational Bayes with Synthetic Likelihood
• Covariances, Robustness, and Variational Bayes
• Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration
• Operator Variational Inference
• Topic-Guided Variational Autoencoders for Text Generation
• Metrics for Deep Generative Models
• Generating Multi-Agent Trajectories using Programmatic Weak Supervision
• Exposure: A White-Box Photo Post-Processing Framework
• Conditional Neural Processes
• Zero-Shot Learning via Class-Conditioned Deep Generative Models
• Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
• Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis
• Disentangling Disentanglement in Variational Autoencoders
• Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
• ControlVAE: Controllable Variational Autoencoder
• Variational inference with a quantum computer
• Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
• Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders
• Variational auto-encoding of protein sequences
• Variational Sequential Monte Carlo
• Image Captioning at Will: A Versatile Scheme for Effectively Injecting Sentiments into Image Descriptions
• Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
• Discriminative Regularization for Generative Models
• IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks
• A neural network walks into a lab: towards using deep nets as models for human behavior
• The Free Energy Principle for Perception and Action: A Deep Learning Perspective
• Model Selection in Bayesian Neural Networks via Horseshoe Priors
• Normalizing Flows on Riemannian Manifolds
• A Hybrid Convolutional Variational Autoencoder for Text Generation
• Stacked Generative Adversarial Networks
• Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
• Effective Image Differencing with ConvNets for Real-time Transient Hunting
• Conditional Variational Autoencoder for Neural Machine Translation
• A Deep Learning Algorithm for High-Dimensional Exploratory Item Factor Analysis
• Recommender systems based on graph embedding techniques: A comprehensive review
• The Mirage of Action-Dependent Baselines in Reinforcement Learning
• Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
• Generative Capacity of Probabilistic Protein Sequence Models
• Multi-View Image Generation from a Single-View
• Neural Adaptive Sequential Monte Carlo
• On the ability of neural nets to express distributions
• Discrete Variational Autoencoders
• Generative Neural Machine Translation
• Neural Predictive Belief Representations
• Linear dynamical neural population models through nonlinear embeddings
• Comparison of Maximum Likelihood and GAN-based training of Real NVPs
• Generative Temporal Models with Memory
• Language as a Latent Variable: Discrete Generative Models for Sentence Compression
• Equivariant Hamiltonian Flows
• Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search
• Fixing a Broken ELBO
• On Disentangled Representations Learned From Correlated Data
• Adversarially Regularized Autoencoders
• Techniques for Learning Binary Stochastic Feedforward Neural Networks
• Unsupervised Model Selection for Variational Disentangled Representation Learning
• Sequence Modeling via Segmentations
• Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC
• SEALion: a Framework for Neural Network Inference on Encrypted Data
• Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging
• Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data
• Adversarial Symmetric Variational Autoencoder
• Riemannian Continuous Normalizing Flows
• A Causal View on Robustness of Neural Networks
• Differentiable Strong Lensing: Uniting Gravity and Neural Nets through Differentiable Probabilistic Programming
• Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
• Avoiding Latent Variable Collapse With Generative Skip Models
• Simple and Effective VAE Training with Calibrated Decoders
• Deconfounding Reinforcement Learning in Observational Settings
• Stochastic Backpropagation through Mixture Density Distributions
• Can multi-label classification networks know what they don't know?
• Deep learning methods in speaker recognition: a review
• A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
• Variational Bayes survival analysis for unemployment modelling
• Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
• Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs
• Semi-Amortized Variational Autoencoders
• Variational Neural Machine Translation
• When Deep Learning Meets Multi-Task Learning in SAR ATR: Simultaneous Target Recognition and Segmentation
• Deep Recurrent Generative Decoder for Abstractive Text Summarization
• Understanding Visual Concepts with Continuation Learning
• Joint embedding of structure and features via graph convolutional networks
• Efficient inference in occlusion-aware generative models of images
• The Functional Neural Process
• A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games
• A Tutorial on Deep Latent Variable Models of Natural Language
• Towards Open-Set Identity Preserving Face Synthesis
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• Entity Abstraction in Visual Model-Based Reinforcement Learning
• Robust Out-of-distribution Detection for Neural Networks
• Autoregressive Quantile Networks for Generative Modeling
• Uncertainty Quantification and Deep Ensembles
• Pixel Deconvolutional Networks
• Improving Variational Encoder-Decoders in Dialogue Generation
• Auto-Encoding Total Correlation Explanation
• Adversarial Distillation of Bayesian Neural Network Posteriors
• GenNI: Human-AI Collaboration for Data-Backed Text Generation
• A Study of the Generalizability of Self-Supervised Representations
• On the challenges of learning with inference networks on sparse, high-dimensional data
• Diffusion Variational Autoencoders
• On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
• Discrete and continuous representations and processing in deep learning: Looking forward
• Variational autoencoder reconstruction of complex many-body physics
• A Conditional Variational Framework for Dialog Generation
• A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks
• Model-Based Policy Search Using Monte Carlo Gradient Estimation with Real Systems Application
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Counterfactuals uncover the modular structure of deep generative models
• Amortized Variational Inference: A Systematic Review
• The Generalized Reparameterization Gradient
• Hamiltonian Generative Networks
• Tighter Variational Bounds are Not Necessarily Better
• Patent Data for Engineering Design: A Critical Review and Future Directions
• Reweighted Wake-Sleep
• Modeling documents with Generative Adversarial Networks
• The Dynamic Embedded Topic Model
• Recurrent Gaussian Processes
• GAR: An efficient and scalable Graph-based Activity Regularization for semi-supervised learning
• Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
• Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective
• Noisy Natural Gradient as Variational Inference
• Semi-Implicit Variational Inference
• Latent Intention Dialogue Models
• Robust Locally-Linear Controllable Embedding
• Black-box Variational Inference for Stochastic Differential Equations
• Nonlinear Invariant Risk Minimization: A Causal Approach
• Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement
• Approximate Inference with Amortised MCMC
• Black-box Adversarial Attacks with Bayesian Optimization
• Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs
• Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
• Turbulence forecasting via Neural ODE
• Improving black-box optimization in VAE latent space using decoder uncertainty
• Learning FRAME Models Using CNN Filters
• Enabling hyperparameter optimization in sequential autoencoders for spiking neural data
• Fast amortized inference of neural activity from calcium imaging data with variational autoencoders
• Perfect density models cannot guarantee anomaly detection
• Learning with hidden variables
• Information bottleneck through variational glasses
• Probabilistic Model-Agnostic Meta-Learning
• Action and Perception as Divergence Minimization
• Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization
• Neural Language Generation: Formulation, Methods, and Evaluation
• Dr.VAE: Drug Response Variational Autoencoder
• A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids
• Mastering Atari with Discrete World Models
• Meta-Learning Deep Energy-Based Memory Models
• Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models
• Poincaré Wasserstein Autoencoder
• Self-Supervised Variational Auto-Encoders
• Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
• Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
• Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow
• Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
• Decompose to manipulate: Manipulable Object Synthesis in 3D Medical Images with Structured Image Decomposition
• not-MIWAE: Deep Generative Modelling with Missing not at Random Data
• Variational Information Bottleneck for Unsupervised Clustering: Deep Gaussian Mixture Embedding
• Approximate Bayesian Model Inversion for PDEs with Heterogeneous and State-Dependent Coefficients
• Counterfactual Inference for Consumer Choice Across Many Product Categories
• DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting
• Adversarial Attacks on Variational Autoencoders
• Deep Learning for Vision-based Prediction: A Survey
• Learnable Bernoulli Dropout for Bayesian Deep Learning
• Fast and Provable ADMM for Learning with Generative Priors
• Variational Memory Addressing in Generative Models
• Deformable Generator Networks: Unsupervised Disentanglement of Appearance and Geometry
• Gaussian Process Prior Variational Autoencoders
• Variational Item Response Theory: Fast, Accurate, and Expressive
• State Alignment-based Imitation Learning
• Deep Factors with Gaussian Processes for Forecasting
• Generative Latent Flow
• Evaluating uncertainties in electrochemical impedance spectra of solid oxide fuel cells
• Deep Directed Generative Autoencoders
• Learning to Learn Variational Semantic Memory
• Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse
• Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection
• Evaluating deep variational autoencoders trained on pan-cancer gene expression
• Differentiable Causal Discovery from Interventional Data
• A Spectral Regularizer for Unsupervised Disentanglement
• Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
• Unsupervised Person Image Synthesis in Arbitrary Poses
• Variational Inference with NoFAS: Normalizing Flow with Adaptive Surrogate for Computationally Expensive Models
• Bayesian Graph Neural Networks with Adaptive Connection Sampling
• Dynamics-aware Embeddings
• Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation
• Robust Learning Under Label Noise With Iterative Noise-Filtering
• The Riemannian Geometry of Deep Generative Models
• A Hierarchical Latent Structure for Variational Conversation Modeling
• Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions
• Bayesian Semisupervised Learning with Deep Generative Models
• Scalable Gaussian Process Variational Autoencoders
• Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow
• Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation
• Towards meaningful physics from generative models
• Shaping Belief States with Generative Environment Models for RL
• Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach
• Invertible Kernel PCA with Random Fourier Features
• Neural Net Models for Open-Domain Discourse Coherence
• Escaping the curse of dimensionality in Bayesian model based clustering
• Autoencoding Low-Resolution MRI for Semantically Smooth Interpolation of Anisotropic MRI
• Fair Generative Modeling via Weak Supervision
• Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing Systems
• A Generative Model of Galactic Dust Emission Using Variational Inference
• Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations
• Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
• Ranking CGANs: Subjective Control over Semantic Image Attributes
• Spatial Uncertainty Sampling for End-to-End Control
• Bayesian Hypernetworks
• Learning about learning by many-body systems
• Sliced Kernelized Stein Discrepancy
• Variance Networks: When Expectation Does Not Meet Your Expectations
• Vprop: Variational Inference using RMSprop
• Behavior Priors for Efficient Reinforcement Learning
• Variational Inference with Hamiltonian Monte Carlo
• Deep Feature Consistent Variational Autoencoder
• Explicit Disentanglement of Appearance and Perspective in Generative Models
• Disentangled State Space Representations
• Overdispersed Black-Box Variational Inference
• PixelVAE++: Improved PixelVAE with Discrete Prior
• Associative Compression Networks for Representation Learning
• VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
• Motion Prediction Under Multimodality with Conditional Stochastic Networks
• Preventing Posterior Collapse with delta-VAEs
• Non-linear Multitask Learning with Deep Gaussian Processes
• A probabilistic deep learning model of inter-fraction anatomical variations in radiotherapy
• Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction
• Densities of Almost Surely Terminating Probabilistic Programs are Differentiable Almost Everywhere
• Muesli: Combining Improvements in Policy Optimization
• A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise
• Big Learning with Bayesian Methods
• High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks
• High-dimensional separability for one- and few-shot learning
• Geodesic Clustering in Deep Generative Models
• GNN is a Counter? Revisiting GNN for Question Answering
• Point Cloud Instance Segmentation using Probabilistic Embeddings
• Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net
• Hyperparameter Auto-tuning in Self-Supervised Robotic Learning
• Variational Laplace Autoencoders
• Clockwork Variational Autoencoders
• TVAE: Triplet-Based Variational Autoencoder using Metric Learning
• COIL: Constrained Optimization in Learned Latent Space: Learning Representations for Valid Solutions
• Topic Memory Networks for Short Text Classification
• Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems
• Learning and controlling the source-filter representation of speech with a variational autoencoder
• Adversarial Examples on Object Recognition: A Comprehensive Survey
• Generative Graph Convolutional Network for Growing Graphs
• PredDiff: Explanations and Interactions from Conditional Expectations
• Learning to Learn with Variational Information Bottleneck for Domain Generalization
• Predicting potential drug targets and repurposable drugs for COVID-19 via a deep generative model for graphs
• X-ray Study of Spatial Structures in Tycho's Supernova Remnant Using Unsupervised Deep Learning
• Inference in Deep Networks in High Dimensions
• Primal-Dual Wasserstein GAN
• Reweighted Expectation Maximization
• Functional Tensors for Probabilistic Programming
• Learning document embeddings along with their uncertainties
• Bilateral Denoising Diffusion Models
• Bounded Information Rate Variational Autoencoders
• Identification of Gaussian Process State Space Models
• Semi-Supervised Generation with Cluster-aware Generative Models
• DiCE: The Infinitely Differentiable Monte-Carlo Estimator
• Query Focused Multi-Document Summarization with Distant Supervision
• Fast Adaptation in Generative Models with Generative Matching Networks
• Multi-task Batch Reinforcement Learning with Metric Learning
• On the Transfer of Disentangled Representations in Realistic Settings
• Leveraging the Exact Likelihood of Deep Latent Variable Models
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
• Smoothed Action Value Functions for Learning Gaussian Policies
• Variational Neural Discourse Relation Recognizer
• Bayesian Incremental Learning for Deep Neural Networks
• Learning to Predict Without Looking Ahead: World Models Without Forward Prediction
• Structured Black Box Variational Inference for Latent Time Series Models
• A Contrastive Learning Approach for Training Variational Autoencoder Priors
• Reparameterization Gradient for Non-differentiable Models
• Meta-Amortized Variational Inference and Learning
• Variational Implicit Processes
• Towards Information-Seeking Agents
• Interpreting Deep Neural Networks Through Variable Importance
• MA-VAE: Multi-head Attention-based Variational Autoencoder Approach for Anomaly Detection in Multivariate Time-series Applied to Automotive Endurance Powertrain Testing
• Nonlinear Statistical Learning with Truncated Gaussian Graphical Models
• On the Road with 16 Neurons: Mental Imagery with Bio-inspired Deep Neural Networks
• Comparison of Affine and Rational Quadratic Spline Coupling and Autoregressive Flows through Robust Statistical Tests
• Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values
• Triple Generative Adversarial Networks
• Towards neural networks that provably know when they don't know
• Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model
• Regularized Autoencoders via Relaxed Injective Probability Flow
• Adversarial Approximate Inference for Speech to Electroglottograph Conversion
• Towards Automatic Image Editing: Learning to See another You
• p-FP: Extraction, Classification, and Prediction of Website Fingerprints with Deep Learning
• Interpretable VAEs for nonlinear group factor analysis
• Using Large Ensembles of Control Variates for Variational Inference
• Towards a Near Universal Time Series Data Mining Tool: Introducing the Matrix Profile
• Bottleneck Conditional Density Estimation
• Deep Probabilistic Programming Languages: A Qualitative Study
• Disentangling and Learning Robust Representations with Natural Clustering
• Differentiable Particle Filtering without Modifying the Forward Pass
• Deep density networks and uncertainty in recommender systems
• Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models
• Variational Variance: Simple, Reliable, Calibrated Heteroscedastic Noise Variance Parameterization
• Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures
• Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling
• Robust Deep Gaussian Processes
• Parametric Gaussian Process Regressors
• Wasserstein Variational Inference
• BasisVAE: Translation-invariant feature-level clustering with Variational Autoencoders
• Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo
• A Flexible Framework for Anomaly Detection via Dimensionality Reduction
• AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning
• Neural Structural Correspondence Learning for Domain Adaptation
• EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
• Deep Quantization: Encoding Convolutional Activations with Deep Generative Model
• Inducing Interpretable Representations with Variational Autoencoders
• Perturbative Black Box Variational Inference
• Uncertainty Inspired RGB-D Saliency Detection
• Deep Involutive Generative Models for Neural MCMC
• Super-resolution Variational Auto-Encoders
• Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets
• Active Divergence with Generative Deep Learning -- A Survey and Taxonomy
• Structured Generative Models for Scene Understanding
• Exploring Uncertainty in Deep Learning for Construction of Prediction Intervals
• Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions
• Variational Inference for Deblending Crowded Starfields
• Predictive Sampling with Forecasting Autoregressive Models
• Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction
• The Differentiable Cross-Entropy Method
• Generative Models For Deep Learning with Very Scarce Data
• Data Augmentation for Bayesian Deep Learning
• Adversarial Defense of Image Classification Using a Variational Auto-Encoder
• Neural Variational Hybrid Collaborative Filtering
• Hierarchical VampPrior Variational Fair Auto-Encoder
• Gaussian mixture models with Wasserstein distance
• Recurrent Neural Network-Based Semantic Variational Autoencoder for Sequence-to-Sequence Learning
• A Structured Variational Auto-encoder for Learning Deep Hierarchies of Sparse Features
• Stochastic Neural Networks with Monotonic Activation Functions
• Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server
• Learning High-level Prior with Convolutional Neural Networks for Semantic Segmentation
• Automatic Relevance Determination For Deep Generative Models
• Scaling Factorial Hidden Markov Models: Stochastic Variational Inference without Messages
• Automatic Variational ABC
• Topographic VAEs learn Equivariant Capsules
• MissDeepCausal: Causal Inference from Incomplete Data Using Deep Latent Variable Models
• Hierarchical Approaches for Reinforcement Learning in Parameterized Action Space
• Learning Discrete State Abstractions With Deep Variational Inference
• Variational Inference In Pachinko Allocation Machines
• Efficient non-conjugate Gaussian process factor models for spike count data using polynomial approximations
• Multimodal Generative Models for Compositional Representation Learning
• Deep Variational Sufficient Dimensionality Reduction
• Generate High Resolution Images With Generative Variational Autoencoder
• Semi-Recurrent CNN-based VAE-GAN for Sequential Data Generation
• Variational inference based on a subclass of closed skew normals
• Bayesian Neural Networks at Scale: A Performance Analysis and Pruning Study
• High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection
• Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case
• The Posterior Predictive Null
• A Variational Autoencoder for Probabilistic Non-Negative Matrix Factorisation
• Investigation of Using VAE for i-Vector Speaker Verification
• Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models
• Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation
• Sampling-based probabilistic inference emerges from learning in neural circuits with a cost on reliability
• Text-to-Image Generation with Attention Based Recurrent Neural Networks
• Variational Generative Stochastic Networks with Collaborative Shaping
• Structured Embedding Models for Grouped Data
• CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarios
• Recursive Inference for Variational Autoencoders
• Variational Autoencoder with Implicit Optimal Priors
• Geometry-Aware Hamiltonian Variational Auto-Encoder
• Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction
• Deep Variational Inference Without Pixel-Wise Reconstruction
• Training VAEs Under Structured Residuals
• A Brief Overview of Unsupervised Neural Speech Representation Learning
• Independent finite approximations for Bayesian nonparametric inference
• mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation
• Generalization and Robustness Implications in Object-Centric Learning
• HyperFlow: Representing 3D Objects as Surfaces
• Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks
• Hybrid VAE: Improving Deep Generative Models using Partial Observations
• A Method to Model Conditional Distributions with Normalizing Flows
• Factored Temporal Sigmoid Belief Networks for Sequence Learning
• Improving Sequential Latent Variable Models with Autoregressive Flows
• A Deep Learning and Gamification Approach to Energy Conservation at Nanyang Technological University
• Importance Weighted Adversarial Variational Autoencoders for Spike Inference from Calcium Imaging Data
• Augment and Reduce: Stochastic Inference for Large Categorical Distributions
• MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference
• Hamiltonian Variational Auto-Encoder
• Representation learning for improved interpretability and classification accuracy of clinical factors from EEG
• Spatial PixelCNN: Generating Images from Patches
• Variational Inference for Data-Efficient Model Learning in POMDPs
• TURBO: The Swiss Knife of Auto-Encoders
• Hierarchical CVAE for Fine-Grained Hate Speech Classification
• Simple Video Generation using Neural ODEs
• Do sequence-to-sequence VAEs learn global features of sentences?
• Approximating exponential family models (not single distributions) with a two-network architecture
• Label-Noise Robust Multi-Domain Image-to-Image Translation
• Joint Stochastic Approximation learning of Helmholtz Machines
• Variational Autoencoder Kernel Interpretation and Selection for Classification
• VarFA: A Variational Factor Analysis Framework For Efficient Bayesian Learning Analytics
• DynamicVAE: Decoupling Reconstruction Error and Disentangled Representation Learning
• Latent Programmer: Discrete Latent Codes for Program Synthesis
• Learning robust speech representation with an articulatory-regularized variational autoencoder
• Reinforced Deep Markov Models With Applications in Automatic Trading
• Relation Learning on Social Networks with Multi-Modal Graph Edge Variational Autoencoders
• A Batch Normalized Inference Network Keeps the KL Vanishing Away
• Data Smashing 2.0: Sequence Likelihood (SL) Divergence For Fast Time Series Comparison
• A Simple Framework for Uncertainty in Contrastive Learning
• Increasing Expressivity of a Hyperspherical VAE
• Robust Variational Autoencoders for Outlier Detection and Repair of Mixed-Type Data
• To Relieve Your Headache of Training an MRF, Take AdVIL
• Deep Variational Transfer: Transfer Learning through Semi-supervised Deep Generative Models
• Oversampling Log Messages Using a Sequence Generative Adversarial Network for Anomaly Detection and Classification
• Neural Pharmacodynamic State Space Modeling
• Annealed Flow Transport Monte Carlo
• An Uncertain Future: Forecasting from Static Images using Variational Autoencoders
• Accelerate CNN via Recursive Bayesian Pruning
• InfoFair: Information-Theoretic Intersectional Fairness
• The LORACs prior for VAEs: Letting the Trees Speak for the Data
• Bayesian Paragraph Vectors
• Adaptive Pruning of Neural Language Models for Mobile Devices
• Latent Topic Conversational Models
• SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation
• Variational Capsules for Image Analysis and Synthesis
• Flow Contrastive Estimation of Energy-Based Models
• Bayesian Optimization Algorithms for Accelerator Physics
• Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections
• A Novel Variational Autoencoder with Applications to Generative Modelling, Classification, and Ordinal Regression
• Double Backpropagation for Training Autoencoders against Adversarial Attack
• Variational Auto-Encoder: not all failures are equal
• Predictive Coding for Locally-Linear Control
• Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding
• Modelling Latent Skills for Multitask Language Generation
• Sliced Iterative Normalizing Flows
• Auto-clustering Output Layer: Automatic Learning of Latent Annotations in Neural Networks
• Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns
• Semi-unsupervised Learning of Human Activity using Deep Generative Models
• CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation
• Teaching deep neural networks to localize single molecules for super-resolution microscopy
• Continuously tempered Hamiltonian Monte Carlo
• Linear Algebra and Duality of Neural Networks
• AMENet: Attentive Maps Encoder Network for Trajectory Prediction
• Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy
• Backprop-Q: Generalized Backpropagation for Stochastic Computation Graphs
• Causal Effect Variational Autoencoder with Uniform Treatment
• Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
• Bayesian Learning of Probabilistic Dipole Inversion for Quantitative Susceptibility Mapping
• CSI Clustering with Variational Autoencoding
• Effect of latent space distribution on the segmentation of images with multiple annotations
• Reconstruction of Simulation-Based Physical Field by Reconstruction Neural Network Method
• Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach
• Decomposed Adversarial Learned Inference
• Face Reconstruction with Variational Autoencoder and Face Masks
• FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
• Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data
• Variational Rejection Sampling
• Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
• Segment-Based Credit Scoring Using Latent Clusters in the Variational Autoencoder
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
• Text Data Augmentation: Towards better detection of spear-phishing emails
• Iterative Refinement of the Approximate Posterior for Directed Belief Networks
• High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curve
• Discond-VAE: Disentangling Continuous Factors from the Discrete
• Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning
• Improving Bi-directional Generation between Different Modalities with Variational Autoencoders
• SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation
• Towards Amortized Ranking-Critical Training for Collaborative Filtering
• Improved Variational Neural Machine Translation by Promoting Mutual Information
• LAVAE: Disentangling Location and Appearance
• DPD-InfoGAN: Differentially Private Distributed InfoGAN
• Sensorimotor Visual Perception on Embodied System Using Free Energy Principle
• Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)
• Filtering Variational Objectives
• Rare Event Detection using Disentangled Representation Learning
• Factorized Gaussian Process Variational Autoencoders
• Backpropagation for Implicit Spectral Densities
• Iterative VAE as a predictive brain model for out-of-distribution generalization
• Symmetries and control in generative neural nets
• The use of Generative Adversarial Networks to characterise new physics in multi-lepton final states at the LHC
• Unsupervised preprocessing for Tactile Data
• Fast Approximate Geodesics for Deep Generative Models
• GSNs : Generative Stochastic Networks
• Texture Synthesis with Recurrent Variational Auto-Encoder
• Variational inference of latent state sequences using Recurrent Networks
• Woodbury Transformations for Deep Generative Flows
• Certifiably Robust Variational Autoencoders
• Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation
• Model-agnostic out-of-distribution detection using combined statistical tests
• Max-Margin Deep Generative Models for (Semi-)Supervised Learning
• Multi-type Disentanglement without Adversarial Training
• Estimating Granger Causality with Unobserved Confounders via Deep Latent-Variable Recurrent Neural Network
• Estimating Nonlinear Dynamics with the ConvNet Smoother
• Local Clustering with Mean Teacher for Semi-supervised Learning
• Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
• Flexible mean field variational inference using mixtures of non-overlapping exponential families
• Artificial Neural Networks Jamming on the Beat
• Neural Variational Inference and Learning in Undirected Graphical Models
• Variational Inference for Deep Probabilistic Canonical Correlation Analysis
• Learning a Hierarchical Latent-Variable Model of 3D Shapes
• Human Pose Forecasting via Deep Markov Models
• Hidden Markov Neural Networks
• Assessing Deep Neural Networks as Probability Estimators
• Deep kernel processes
• Improving Fair Predictions Using Variational Inference In Causal Models
• Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds
• Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning
• Semi-supervised Sequential Generative Models
• Neural Likelihoods for Multi-Output Gaussian Processes
• Variational Bayes: A report on approaches and applications
• On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods
• Deep learning based inverse method for layout design
• Likelihood Contribution based Multi-scale Architecture for Generative Flows
• Learning Controllable Disentangled Representations with Decorrelation Regularization
• Can VAEs Generate Novel Examples?
• Precision-Recall Curves Using Information Divergence Frontiers
• Pseudo-Encoded Stochastic Variational Inference
• Discrete flow posteriors for variational inference in discrete dynamical systems
• Amortized Population Gibbs Samplers with Neural Sufficient Statistics
• Inverting Variational Autoencoders for Improved Generative Accuracy
• Deep Consensus Learning
• A Goal-Based Movement Model for Continuous Multi-Agent Tasks
• On Masked Pre-training and the Marginal Likelihood
• Energy-Based Processes for Exchangeable Data
• Automated Label Generation for Time Series Classification with Representation Learning: Reduction of Label Cost for Training
• Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation
• ControlVAE: Tuning, Analytical Properties, and Performance Analysis
• Towards universal neural nets: Gibbs machines and ACE
• Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds
• Bayesian Models for Heterogeneous Personalized Health Data
• DeepCoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding
• Deep Unsupervised Clustering with Clustered Generator Model
• HRINet: Alternative Supervision Network for High-resolution CT image Interpolation
• MCENET: Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic
• Learning Bijective Feature Maps for Linear ICA
• Cooperative image captioning
• Learning GPLVM with arbitrary kernels using the unscented transformation
• LioNets: Local Interpretation of Neural Networks through Penultimate Layer Decoding
• Neural Communication Systems with Bandwidth-limited Channel
• Capsule Networks -- A Probabilistic Perspective
• Variational Auto-Decoder: A Method for Neural Generative Modeling from Incomplete Data
• From Rain Generation to Rain Removal
• Re-examination of the Role of Latent Variables in Sequence Modeling
• Conditioning Trick for Training Stable GANs
• Dream and Search to Control: Latent Space Planning for Continuous Control
• Efficient and Robust Machine Learning for Real-World Systems
• Closed Form Variational Objectives For Bayesian Neural Networks with a Single Hidden Layer
• Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
• Multi-Source Neural Variational Inference
• Fitting summary statistics of neural data with a differentiable spiking network simulator
• Deep Generative Model with Beta Bernoulli Process for Modeling and Learning Confounding Factors
• TzK Flow - Conditional Generative Model
• Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference
• Gaussian variational approximation with a factor covariance structure
• L-Verse: Bidirectional Generation Between Image and Text
• Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations
• Learning a Representation Map for Robot Navigation using Deep Variational Autoencoder
• Improving latent variable descriptiveness with AutoGen
• Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
• Explaining Away Syntactic Structure in Semantic Document Representations
• Excavate Condition-invariant Space by Intrinsic Encoder
• Pathwise Derivatives for Multivariate Distributions
• Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
• Neural Contractive Dynamical Systems
• Generative Creativity: Adversarial Learning for Bionic Design
• Unsupervised Representation Adversarial Learning Network: from Reconstruction to Generation
• Acoustic feature learning using cross-domain articulatory measurements
• Cascaded Head-colliding Attention
• Hierarchical Video Generation for Complex Data
• Quantifying Uncertainty in Deep Spatiotemporal Forecasting
• Dimension-free Information Concentration via Exp-Concavity
• Convex Smoothed Autoencoder-Optimal Transport model
• Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE
• Cauchy-Schwarz Regularized Autoencoder
• Variational Knowledge Distillation for Disease Classification in Chest X-Rays
• Unsupervised Disentanglement of Linear-Encoded Facial Semantics
• Scaling Bayesian inference of mixed multinomial logit models to very large datasets
• Learning and Inference in Imaginary Noise Models
• Reinforcement Learning as Iterative and Amortised Inference
• Discrete Point Flow Networks for Efficient Point Cloud Generation
• LaDDer: Latent Data Distribution Modelling with a Generative Prior
• Supervised Vector Quantized Variational Autoencoder for Learning Interpretable Global Representations
• Stabilising priors for robust Bayesian deep learning
• Bridging the ELBO and MMD
• Integrating Markov processes with structural causal modeling enables counterfactual inference in complex systems
• Learning undirected models via query training
• Reinforcement Learning with Convolutional Reservoir Computing
• Hierarchical Variational Imitation Learning of Control Programs
• AE-OT-GAN: Training GANs from data specific latent distribution
• Facial Attribute Capsules for Noise Face Super Resolution
• Latent Variable Algorithms for Multimodal Learning and Sensor Fusion
• Representation Learning for Words and Entities
• Perturbation theory approach to study the latent space degeneracy of Variational Autoencoders
• Convolutional Reservoir Computing for World Models
• Note on the equivalence of hierarchical variational models and auxiliary deep generative models
• A Contemporary Overview of Probabilistic Latent Variable Models
• Semi-parametric Network Structure Discovery Models
• Latent Regression Bayesian Network for Data Representation
• Soft-Deep Boltzmann Machines
• CTNN: Corticothalamic-inspired neural network
• Disentangling the Spatial Structure and Style in Conditional VAE
• Scalable Modeling of Spatiotemporal Data using the Variational Autoencoder: an Application in Glaucoma
• No Representation without Transformation
• The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders
• GP-ALPS: Automatic Latent Process Selection for Multi-Output Gaussian Process Models
• Dist-GAN: An Improved GAN using Distance Constraints
• Adaptation of Quadruped Robot Locomotion with Meta-Learning
• A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling
• Modeling Grasp Motor Imagery through Deep Conditional Generative Models
• Neural Options Pricing
• Bayesian task embedding for few-shot Bayesian optimization
• Towards Automatic Sizing for PPE with a Point Cloud Based Variational Autoencoder
• From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder
• Mutual Information Constraints for Monte-Carlo Objectives
• Variational Laplace for Bayesian neural networks
• Variational Composite Autoencoders
• Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements
• EvoVGM: a Deep Variational Generative Model for Evolutionary Parameter Estimation
• Deep Generative Networks For Sequence Prediction
• Automatic generation of object shapes with desired functionalities
• Learning Sparsity of Representations with Discrete Latent Variables
• KF-LAX: Kronecker-factored curvature estimation for control variate optimization in reinforcement learning
• Learning from Multiple Sources for Data-to-Text and Text-to-Data
• Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval
• Forward Amortized Inference for Likelihood-Free Variational Marginalization
• Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
• Approximate Logic Synthesis: A Reinforcement Learning-Based Technology Mapping Approach
• Auto-encoding GPS data to reveal individual and collective behaviour
• Prior Flow Variational Autoencoder: A density estimation model for Non-Intrusive Load Monitoring
• Boosting Summarization with Normalizing Flows and Aggressive Training
• Coarse Grained Exponential Variational Autoencoders
• The Deep Latent Position Topic Model for Clustering and Representation of Networks with Textual Edges
• Counterfactual Supervision-based Information Bottleneck for Out-of-Distribution Generalization
• Incremental Learning from Scratch for Task-Oriented Dialogue Systems
• Attribute-controlled face photo synthesis from simple line drawing
• Latte-Mix: Measuring Sentence Semantic Similarity with Latent Categorical Mixtures
• Deep Measurement Updates for Bayes Filters
• Manifold Optimization Assisted Gaussian Variational Approximation
• Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold
• Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference
• Learning Probabilistic Programs Using Backpropagation
• Video Content Swapping Using GAN
• Switching Recurrent Kalman Networks
• Inner Space Preserving Generative Pose Machine
• Recurrent Flow Networks: A Recurrent Latent Variable Model for Density Modelling of Urban Mobility
• A Fourier View of REINFORCE
• Quantization-Based Regularization for Autoencoders
• Generative learning for deep networks
• Learning disentangled representation for classical models
• KGAN: How to Break The Minimax Game in GAN
• Discovering Influential Factors in Variational Autoencoders
• Detect, anticipate and generate: Semi-supervised recurrent latent variable models for human activity modeling
• Probabilistic Autoencoder using Fisher Information
• Generating new pictures in complex datasets with a simple neural network
• A variational approximate posterior for the deep Wishart process
• Learning to infer in recurrent biological networks
• Concept Formation and Dynamics of Repeated Inference in Deep Generative Models
• Learning Fixation Point Strategy for Object Detection and Classification
• Representation Learning by Reconstructing Neighborhoods
• An Interpretable Generative Model for Handwritten Digit Image Synthesis
• Specializing Word Embeddings (for Parsing) by Information Bottleneck
• Improving Stability of LS-GANs for Audio and Speech Signals
• Unnormalized Variational Bayes
• Differentiable probabilistic programming for strong gravitational lensing
• An Uncertainty-aware Hierarchical Probabilistic Network for Early Prediction, Quantification and Segmentation of Pulmonary Tumour Growth
• Sequential Variational Autoencoders for Collaborative Filtering
• Wavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models
• Maximum Entropy Reinforcement Learning with Mixture Policies
• Noise Contrastive Variational Autoencoders
• Automatic Feature Extraction for Heartbeat Anomaly Detection
• Variational Information Bottleneck Model for Accurate Indoor Position Recognition
• EXoN: EXplainable encoder Network
• Learning Approximately Objective Priors
• Formalising Concepts as Grounded Abstractions
• Testing for Typicality with Respect to an Ensemble of Learned Distributions
• Robust Disentanglement of a Few Factors at a Time
• Refining BERT Embeddings for Document Hashing via Mutual Information Maximization
• Inverse Graphics: Unsupervised Learning of 3D Shapes from Single Images
• Recommending Burgers based on Pizza Preferences: Addressing Data Sparsity with a Product of Experts
• Generation and Simulation of Yeast Microscopy Imagery with Deep Learning
• Constellation: Learning relational abstractions over objects for compositional imagination