Publications (120)
Fast Samplers for Inverse Problems in Iterative Refinement Models
Kushagra Pandey, Ruihan Yang, Stephan Mandt
Constructing fast samplers for unconditional diffusion and flow-matching models has received much attention recently; however, existing methods for solving inverse problems, such a…
Hybridizing Physical and Data-driven Prediction Methods for Physicochemical Properties
Fabian Jirasek, Robert Bamler, Stephan Mandt
We present a generic way to hybridize physical and data-driven methods for predicting physicochemical properties. The approach `distills' the physical method's predictions into a p…
Variational Tempering
Stephan Mandt, James McInerney, Farhan Abrol +2
Variational inference (VI) combined with data subsampling enables approximate posterior inference over large data sets, but suffers from poor local optima. We first formulate a det…
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
Theodore Papamarkou, Maria Skoularidou, Konstantina Palla +22
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language dat…
Stochastic Differential Equations for Quantum Dynamics of Spin-Boson Networks
Stephan Mandt, Darius Sadri, Andrew A. Houck +1
The quantum dynamics of open many-body systems poses a challenge for computational approaches. Here we develop a stochastic scheme based on the positive P phase-space representatio…
Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis
Niluthpol Chowdhury Mithun, Tuan Pham, Qiao Wang +6
Recent advancements in 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have achieved impressive results in real-time 3D reconstruction and novel view synthesis. Howe…
Variational Dynamic Mixtures
Chen Qiu, Stephan Mandt, Maja Rudolph
Deep probabilistic time series forecasting models have become an integral part of machine learning. While several powerful generative models have been proposed, we provide evidence…
Comparing Storm Resolving Models and Climates via Unsupervised Machine Learning
Griffin Mooers, Mike Pritchard, Tom Beucler +5
Global Storm-Resolving Models (GSRMs) have gained widespread interest because of the unprecedented detail with which they resolve the global climate. However, it remains difficult…
Advancing Thermodynamic Group-Contribution Methods by Machine Learning: UNIFAC 2.0
Nicolas Hayer, Thorsten Wendel, Stephan Mandt +2
Accurate prediction of thermodynamic properties is pivotal in chemical engineering for optimizing process efficiency and sustainability. Physical group-contribution (GC) methods ar…
Disentangled Sequential Autoencoder
Yingzhen Li, Stephan Mandt
We present a VAE architecture for encoding and generating high dimensional sequential data, such as video or audio. Our deep generative model learns a latent representation of the…
Preserving Identity with Variational Score for General-purpose 3D Editing
Duong H. Le, Tuan Pham, Aniruddha Kembhavi +3
We present Piva (Preserving Identity with Variational Score Distillation), a novel optimization-based method for editing images and 3D models based on diffusion models. Specificall…
Advances in Variational Inference
Cheng Zhang, Judith Butepage, Hedvig Kjellstrom +1
Many modern unsupervised or semi-supervised machine learning algorithms rely on Bayesian probabilistic models. These models are usually intractable and thus require approximate inf…
Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEs
Harshini Mangipudi, Griffin Mooers, Mike Pritchard +2
Understanding the details of small-scale convection and storm formation is crucial to accurately represent the larger-scale planetary dynamics. Presently, atmospheric scientists ru…
Making Thermodynamic Models of Mixtures Predictive by Machine Learning: Matrix Completion of Pair Interactions
Fabian Jirasek, Robert Bamler, Sophie Fellenz +4
Predictive models of thermodynamic properties of mixtures are paramount in chemical engineering and chemistry. Classical thermodynamic models are successful in generalizing over (c…
Transferring climate change physical knowledge
Francesco Immorlano, Veronika Eyring, Thomas le Monnier de Gouville +5
Precise and reliable climate projections are required for climate adaptation and mitigation, but Earth system models still exhibit great uncertainties. Several approaches have been…
Parallel Token Prediction for Language Models
Felix Draxler, Justus Will, Farrin Marouf Sofian +3
Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework f…
Anomaly Detection of Tabular Data Using LLMs
Aodong Li, Yunhan Zhao, Chen Qiu +4
Large language models (LLMs) have shown their potential in long-context understanding and mathematical reasoning. In this paper, we study the problem of using LLMs to detect tabula…
Probabilistic Querying of Continuous-Time Event Sequences
Alex Boyd, Yuxin Chang, Stephan Mandt +1
Continuous-time event sequences, i.e., sequences consisting of continuous time stamps and associated event types ("marks"), are an important type of sequential data with many appli…
Understanding and Visualizing Droplet Distributions in Simulations of Shallow Clouds
Justus C. Will, Andrea M. Jenney, Kara D. Lamb +7
Thorough analysis of local droplet-level interactions is crucial to better understand the microphysical processes in clouds and their effect on the global climate. High-accuracy si…
Weakly-Supervised Multimodal Learning on MIMIC-CXR
Andrea Agostini, Daphné Chopard, Yang Meng +5
Multimodal data integration and label scarcity pose significant challenges for machine learning in medical settings. To address these issues, we conduct an in-depth evaluation of t…
Learning to Simulate High Energy Particle Collisions from Unlabeled Data
Jessica N. Howard, Stephan Mandt, Daniel Whiteson +1
In many scientific fields which rely on statistical inference, simulations are often used to map from theoretical models to experimental data, allowing scientists to test model pre…
Predictive Querying for Autoregressive Neural Sequence Models
Alex Boyd, Sam Showalter, Stephan Mandt +1
In reasoning about sequential events it is natural to pose probabilistic queries such as "when will event A occur next" or "what is the probability of A occurring before B", with a…
Neural NeRF Compression
Tuan Pham, Stephan Mandt
Neural Radiance Fields (NeRFs) have emerged as powerful tools for capturing detailed 3D scenes through continuous volumetric representations. Recent NeRFs utilize feature grids to…
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Jakub Swiatkowski, Kevin Roth, Bastiaan S. Veeling +7
Variational Bayesian Inference is a popular methodology for approximating posterior distributions over Bayesian neural network weights. Recent work developing this class of methods…
Dynamic Word Embeddings
Robert Bamler, Stephan Mandt
We present a probabilistic language model for time-stamped text data which tracks the semantic evolution of individual words over time. The model represents words and contexts by l…
Control-Augmented Autoregressive Diffusion for Data Assimilation
Prakhar Srivastava, Farrin Marouf Sofian, Francesco Immorlano +2
Despite advances in test-time scaling and diffusion finetuning, guidance for Auto-Regressive Diffusion Models (ARDMs) remains underexplored. We introduce an amortized framework tha…
One Diffusion to Generate Them All
Duong H. Le, Tuan Pham, Sangho Lee +5
We introduce OneDiffusion, a versatile, large-scale diffusion model that seamlessly supports bidirectional image synthesis and understanding across diverse tasks. It enables condit…
Scalable Generalized Dynamic Topic Models
Patrick Jähnichen, Florian Wenzel, Marius Kloft +1
Dynamic topic models (DTMs) model the evolution of prevalent themes in literature, online media, and other forms of text over time. DTMs assume that word co-occurrence statistics c…
Early-Exit Neural Networks with Nested Prediction Sets
Metod Jazbec, Patrick Forré, Stephan Mandt +2
Early-exit neural networks (EENNs) enable adaptive and efficient inference by providing predictions at multiple stages during the forward pass. In safety-critical applications, the…
Comment on "Consistent thermostatistics forbids negative absolute temperatures"
Ulrich Schneider, Stephan Mandt, Akos Rapp +4
In this comment we argue that negative absolute temperatures are a well-established concept for systems with bounded spectra. They are not only consistent with thermodynamics, but…
Deep Generative Video Compression
Jun Han, Salvator Lombardo, Christopher Schroers +1
The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here…
Exponential Family Embeddings
Maja R. Rudolph, Francisco J. R. Ruiz, Stephan Mandt +1
Word embeddings are a powerful approach for capturing semantic similarity among terms in a vocabulary. In this paper, we develop exponential family embeddings, a class of methods t…
On the Challenges and Opportunities in Generative AI
Laura Manduchi, Clara Meister, Kushagra Pandey +23
The field of deep generative modeling has grown rapidly in the last few years. With the availability of massive amounts of training data coupled with advances in scalable unsupervi…
Heavy-Tailed Diffusion Models
Kushagra Pandey, Jaideep Pathak, Yilun Xu +4
Diffusion models achieve state-of-the-art generation quality across many applications, but their ability to capture rare or extreme events in heavy-tailed distributions remains unc…
Progressive Compression with Universally Quantized Diffusion Models
Yibo Yang, Justus C. Will, Stephan Mandt
Diffusion probabilistic models have achieved mainstream success in many generative modeling tasks, from image generation to inverse problem solving. A distinct feature of these mod…
Lossless Compression with Probabilistic Circuits
Anji Liu, Stephan Mandt, Guy Van den Broeck
Despite extensive progress on image generation, common deep generative model architectures are not easily applied to lossless compression. For example, VAEs suffer from a compressi…
Generative Modeling for Atmospheric Convection
Griffin Mooers, Jens Tuyls, Stephan Mandt +2
While cloud-resolving models can explicitly simulate the details of small-scale storm formation and morphology, these details are often ignored by climate models for lack of comput…
Improving Inference for Neural Image Compression
Yibo Yang, Robert Bamler, Stephan Mandt
We consider the problem of lossy image compression with deep latent variable models. State-of-the-art methods build on hierarchical variational autoencoders (VAEs) and learn infere…
Interacting Fermionic Atoms in Optical Lattices Diffuse Symmetrically Upwards and Downwards in a Gravitational Potential
Stephan Mandt, Akos Rapp, Achim Rosch
We consider a cloud of fermionic atoms in an optical lattice described by a Hubbard model with an additional linear potential. While homogeneous interacting systems mainly show dam…
DiffStyleTS: Diffusion Model for Style Transfer in Time Series
Mayank Nagda, Phil Ostheimer, Justus Arweiler +13
Style transfer combines the content of one signal with the style of another. It supports applications such as data augmentation and scenario simulation, helping machine learning mo…
Sparse Data Diffusion for Scientific Simulations in Biology and Physics
Phil Ostheimer, Mayank Nagda, Andriy Balinskyy +5
Sparse data is fundamental to scientific simulations in biology and physics, from single-cell gene expression to particle calorimetry, where exact zeros encode physical absence rat…
Equilibration rates and negative absolute temperatures for ultracold atoms in optical lattices
Akos Rapp, Stephan Mandt, Achim Rosch
As highly tunable interacting systems, cold atoms in optical lattices are ideal to realize and observe negative absolute temperatures, T < 0. We show theoretically that by reversin…
Structure is Supervision: Multiview Masked Autoencoders for Radiology
Sonia Laguna, Andrea Agostini, Alain Ryser +9
Building robust medical machine learning systems requires pretraining strategies that exploit the intrinsic structure present in clinical data. We introduce Multiview Masked Autoen…
Smoothed Gradients for Stochastic Variational Inference
Stephan Mandt, David Blei
Stochastic variational inference (SVI) lets us scale up Bayesian computation to massive data. It uses stochastic optimization to fit a variational distribution, following easy-to-c…
Bayesian Paragraph Vectors
Geng Ji, Robert Bamler, Erik B. Sudderth +1
Word2vec (Mikolov et al., 2013) has proven to be successful in natural language processing by capturing the semantic relationships between different words. Built on top of single-w…
Skipping the Zeros in Diffusion Models for Sparse Data Generation
Phil Sidney Ostheimer, Mayank Nagda, Andriy Balinskyy +6
Diffusion models (DMs) excel on dense continuous data, but are not designed for sparse continuous data. They do not model exact zeros that represent the deliberate absence of a sig…
Hydra: Preserving Ensemble Diversity for Model Distillation
Linh Tran, Bastiaan S. Veeling, Kevin Roth +7
Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory…
GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation
Tuan Pham, Thanh-Tung Le, Xiaohui Xie +1
We introduce a novel framework for metric depth estimation that enhances pretrained diffusion-based monocular depth estimation (DB-MDE) models with stereo vision guidance. While ex…
SetPINNs: Set-based Physics-informed Neural Networks
Mayank Nagda, Phil Ostheimer, Thomas Specht +5
Physics-Informed Neural Networks (PINNs) solve partial differential equations using deep learning. However, conventional PINNs perform pointwise predictions that neglect dependenci…
Variational Bayesian Quantization
Yibo Yang, Robert Bamler, Stephan Mandt
We propose a novel algorithm for quantizing continuous latent representations in trained models. Our approach applies to deep probabilistic models, such as variational autoencoders…
Structured Stochastic Gradient MCMC
Antonios Alexos, Alex Boyd, Stephan Mandt
Stochastic gradient Markov Chain Monte Carlo (SGMCMC) is considered the gold standard for Bayesian inference in large-scale models, such as Bayesian neural networks. Since practiti…
Stochastic Gradient Descent as Approximate Bayesian Inference
Stephan Mandt, Matthew D. Hoffman, David M. Blei
Stochastic Gradient Descent with a constant learning rate (constant SGD) simulates a Markov chain with a stationary distribution. With this perspective, we derive several new resul…
Iterative Amortized Inference
Joseph Marino, Yisong Yue, Stephan Mandt
Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By repla…
Tightening Bounds for Variational Inference by Revisiting Perturbation Theory
Robert Bamler, Cheng Zhang, Manfred Opper +1
Variational inference has become one of the most widely used methods in latent variable modeling. In its basic form, variational inference employs a fully factorized variational di…
Structured Black Box Variational Inference for Latent Time Series Models
Robert Bamler, Stephan Mandt
Continuous latent time series models are prevalent in Bayesian modeling; examples include the Kalman filter, dynamic collaborative filtering, or dynamic topic models. These models…
Supervised Compression for Resource-Constrained Edge Computing Systems
Yoshitomo Matsubara, Ruihan Yang, Marco Levorato +1
There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural netwo…
Zero-Shot Anomaly Detection via Batch Normalization
Aodong Li, Chen Qiu, Marius Kloft +3
Anomaly detection (AD) plays a crucial role in many safety-critical application domains. The challenge of adapting an anomaly detector to drift in the normal data distribution, esp…
Technical Report: Towards Unified Diffusion Models for Multi-Model Climate Emulation at Scale
Francesco Immorlano, Elijah Tavares, Felix Draxler +3
Large ensembles of climate projections are essential for characterizing uncertainty in future climate and extreme weather events, yet computational constraints of numerical climate…
Hierarchical Variational Policies for Reward-Guided Diffusion
Kushagra Pandey, Farrin Marouf Sofian, Jan Niklas Groeneveld +2
Adapting pretrained diffusion models to downstream objectives such as inverse problems often requires expensive test-time guidance or optimization. We propose a principled framewor…
Uncertainty Estimation for Molecular Diffusion Models
Paul Seij, Christian A. Naesseth, Stephan Mandt +1
Diffusion models have seen wide adoption for 3D molecular generation, yet they offer no principled signal of when a generated molecule is likely to be of low quality. We propose a…
Improving Optimization for Models With Continuous Symmetry Breaking
Robert Bamler, Stephan Mandt
Many loss functions in representation learning are invariant under a continuous symmetry transformation. For example, the loss function of word embeddings (Mikolov et al., 2013) re…
Active Mini-Batch Sampling using Repulsive Point Processes
Cheng Zhang, Cengiz Ãztireli, Stephan Mandt +1
The convergence speed of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. We explore sampling schemes where similar data points are less likely…
Scalable Gaussian Process Variational Autoencoders
Metod Jazbec, Matthew Ashman, Vincent Fortuin +3
Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors. Amortized Gaussian process inference through GP-VAEs…
Variational Test-time Optimization for Diffusion Synchronization
Hyunsoo Lee, Farrin Marouf Sofian, Kushagra Pandey +1
Collaborative generation, which coordinates multiple diffusion trajectories to extend the capabilities of pretrained priors, has emerged as a powerful paradigm for extending the ap…
Insights from Generative Modeling for Neural Video Compression
Ruihan Yang, Yibo Yang, Joseph Marino +1
While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this wor…
A Tale of Two Temperatures: Simple, Efficient, and Diverse Sampling from Diffusion Language Models
Theo X. Olausson, Metod Jazbec, Xi Wang +4
Much work has been done on designing fast and accurate sampling for diffusion language models (dLLMs). However, these efforts have largely focused on the tradeoff between speed and…
Determinantal Point Processes for Mini-Batch Diversification
Cheng Zhang, Hedvig Kjellstrom, Stephan Mandt
We study a mini-batch diversification scheme for stochastic gradient descent (SGD). While classical SGD relies on uniformly sampling data points to form a mini-batch, we propose a…
Perturbative Black Box Variational Inference
Robert Bamler, Cheng Zhang, Manfred Opper +1
Black box variational inference (BBVI) with reparameterization gradients triggered the exploration of divergence measures other than the Kullback-Leibler (KL) divergence, such as a…
Damping of Bloch oscillations: Variational solutions of the Boltzmann equation beyond linear response
Stephan Mandt
Variational solutions of the Boltzmann equation usually rely on the concept of linear response. We extend the variational approach for tight-binding models at high entropies to a r…
Unity by Diversity: Improved Representation Learning in Multimodal VAEs
Thomas M. Sutter, Yang Meng, Andrea Agostini +5
Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architec…
Efficient Integrators for Diffusion Generative Models
Kushagra Pandey, Maja Rudolph, Stephan Mandt
Diffusion models suffer from slow sample generation at inference time. Therefore, developing a principled framework for fast deterministic/stochastic sampling for a broader class o…
Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion
Fabian Jirasek, Rodrigo A. S. Alves, Julie Damay +6
Activity coefficients, which are a measure of the non-ideality of liquid mixtures, are a key property in chemical engineering with relevance to modeling chemical and phase equilibr…
Augmenting and Tuning Knowledge Graph Embeddings
Robert Bamler, Farnood Salehi, Stephan Mandt
Knowledge graph embeddings rank among the most successful methods for link prediction in knowledge graphs, i.e., the task of completing an incomplete collection of relational facts…
Generative Uncertainty in Diffusion Models
Metod Jazbec, Eliot Wong-Toi, Guoxuan Xia +3
Diffusion models have recently driven significant breakthroughs in generative modeling. While state-of-the-art models produce high-quality samples on average, individual samples ca…
Thermodynamically consistent machine learning model for excess Gibbs energy
Marco Hoffmann, Thomas Specht, Quirin Göttl +4
The excess Gibbs energy plays a central role in chemical engineering and chemistry, providing a basis for modeling thermodynamic properties of liquid mixtures. Predicting the exces…
Advances in Diffusion-Based Generative Compression
Yibo Yang, Stephan Mandt
Popularized by their strong image generation performance, diffusion and related methods for generative modeling have found widespread success in visual media applications. In parti…
A Complete Recipe for Diffusion Generative Models
Kushagra Pandey, Stephan Mandt
Score-based Generative Models (SGMs) have demonstrated exceptional synthesis outcomes across various tasks. However, the current design landscape of the forward diffusion process r…
Autoregressive Text Generation Beyond Feedback Loops
Florian Schmidt, Stephan Mandt, Thomas Hofmann
Autoregressive state transitions, where predictions are conditioned on past predictions, are the predominant choice for both deterministic and stochastic sequential models. However…
Lossy Image Compression with Conditional Diffusion Models
Ruihan Yang, Stephan Mandt
This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an imag…
Neural Transformation Learning for Deep Anomaly Detection Beyond Images
Chen Qiu, Timo Pfrommer, Marius Kloft +2
Data transformations (e.g. rotations, reflections, and cropping) play an important role in self-supervised learning. Typically, images are transformed into different views, and neu…
How Good is the Bayes Posterior in Deep Neural Networks Really?
Florian Wenzel, Kevin Roth, Bastiaan S. Veeling +7
During the past five years the Bayesian deep learning community has developed increasingly accurate and efficient approximate inference procedures that allow for Bayesian inference…
AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data
Tuan Truong, Rithwik Sudharsan, Yibo Yang +4
The site conditions that make astronomical observatories in space and on the ground so desirable -- cold and dark -- demand a physical remoteness that leads to limited data transmi…
Improving Sequential Latent Variable Models with Autoregressive Flows
Joseph Marino, Lei Chen, Jiawei He +1
We propose an approach for improving sequence modeling based on autoregressive normalizing flows. Each autoregressive transform, acting across time, serves as a moving frame of ref…
Towards Fast Stochastic Sampling in Diffusion Generative Models
Kushagra Pandey, Maja Rudolph, Stephan Mandt
Diffusion models suffer from slow sample generation at inference time. Despite recent efforts, improving the sampling efficiency of stochastic samplers for diffusion models remains…
Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes
Ba-Hien Tran, Babak Shahbaba, Stephan Mandt +1
Autoencoders and their variants are among the most widely used models in representation learning and generative modeling. However, autoencoder-based models usually assume that the…
On the Effect of Regularization on Nonparametric Mean-Variance Regression
Eliot Wong-Toi, Alex Boyd, Vincent Fortuin +1
Uncertainty quantification is vital for decision-making and risk assessment in machine learning. Mean-variance regression models, which predict both a mean and residual noise for e…
Region-Adaptive Generative Compression with Spatially Varying Diffusion Models
Lucas Relic, Roberto Azevedo, Yang Zhang +3
Generative image codecs aim to optimize perceptual quality, producing realistic and detailed reconstructions. However, they often overlook a key property of human vision: our tende…
Raising the Bar in Graph-level Anomaly Detection
Chen Qiu, Marius Kloft, Stephan Mandt +1
Graph-level anomaly detection has become a critical topic in diverse areas, such as financial fraud detection and detecting anomalous activities in social networks. While most rese…
Understanding Pathologies of Deep Heteroskedastic Regression
Eliot Wong-Toi, Alex Boyd, Vincent Fortuin +1
Deep, overparameterized regression models are notorious for their tendency to overfit. This problem is exacerbated in heteroskedastic models, which predict both mean and residual n…
An Introduction to Neural Data Compression
Yibo Yang, Stephan Mandt, Lucas Theis
Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new…
A Scale-Adaptive Framework for Joint Spatiotemporal Super-Resolution with Diffusion Models
Max Defez, Filippo Quarenghi, Mathieu Vrac +2
Deep-learning video super-resolution has progressed rapidly, but climate applications typically super-resolve (increase resolution) either space or time, and joint spatiotemporal m…
Diffusion Probabilistic Modeling for Video Generation
Ruihan Yang, Prakhar Srivastava, Stephan Mandt
Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability t…
Precipitation Downscaling with Spatiotemporal Video Diffusion
Prakhar Srivastava, Ruihan Yang, Gavin Kerrigan +4
In climate science and meteorology, high-resolution local precipitation (rain and snowfall) predictions are limited by the computational costs of simulation-based methods. Statisti…
Deep Anomaly Detection on Tennessee Eastman Process Data
Fabian Hartung, Billy Joe Franks, Tobias Michels +15
This paper provides the first comprehensive evaluation and analysis of modern (deep-learning) unsupervised anomaly detection methods for chemical process data. We focus on the Tenn…
Latent Outlier Exposure for Anomaly Detection with Contaminated Data
Chen Qiu, Aodong Li, Marius Kloft +2
Anomaly detection aims at identifying data points that show systematic deviations from the majority of data in an unlabeled dataset. A common assumption is that clean training data…
A Variational Analysis of Stochastic Gradient Algorithms
Stephan Mandt, Matthew D. Hoffman, David M. Blei
Stochastic Gradient Descent (SGD) is an important algorithm in machine learning. With constant learning rates, it is a stochastic process that, after an initial phase of convergenc…
Detecting Anomalies within Time Series using Local Neural Transformations
Tim Schneider, Chen Qiu, Marius Kloft +4
We develop a new method to detect anomalies within time series, which is essential in many application domains, reaching from self-driving cars, finance, and marketing to medical d…
UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis
Thanh-Tung Le, Tuan Pham, Tung Nguyen +3
Novel view synthesis (NVS) seeks to render photorealistic, 3D-consistent images of a scene from unseen camera poses given only a sparse set of posed views. Existing deterministic n…
Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning
Aodong Li, Alex Boyd, Padhraic Smyth +1
We consider the problem of online learning in the presence of distribution shifts that occur at an unknown rate and of unknown intensity. We derive a new Bayesian online inference…
Understanding Extreme Precipitation Changes through Unsupervised Machine Learning
Griffin Mooers, Tom Beucler, Mike Pritchard +1
Despite the importance of quantifying how the spatial patterns of extreme precipitation will change with warming, we lack tools to objectively analyze the storm-scale outputs of mo…