b'Stephan Mandt'

research

∙ 06/29/2023

Understanding Pathologies of Deep Heteroskedastic Regression

Several recent studies have reported negative results when using heteros...

0 Eliot Wong-Toi, et al. ∙

research

∙ 06/14/2023

ClimSim: An open large-scale dataset for training high-resolution physics emulators in hybrid multi-scale climate simulators

Modern climate projections lack adequate spatial and temporal resolution...

8 Sungduk Yu, et al. ∙

research

∙ 04/13/2023

Asymmetrically-powered Neural Image Compression with Shallow Decoders

Neural image compression methods have seen increasingly strong performan...

0 Yibo Yang, et al. ∙

research

∙ 03/10/2023

Deep Anomaly Detection on Tennessee Eastman Process Data

This paper provides the first comprehensive evaluation and analysis of m...

0 Fabian Hartung, et al. ∙

research

∙ 03/03/2023

Generative Diffusions in Augmented Spaces: A Complete Recipe

Score-based Generative Models (SGMs) have achieved state-of-the-art synt...

0 kushagra-pandey, et al. ∙

research

∙ 02/15/2023

Zero-Shot Anomaly Detection without Foundation Models

Anomaly detection (AD) tries to identify data instances that deviate fro...

0 Aodong Li, et al. ∙

research

∙ 02/15/2023

Deep Anomaly Detection under Labeling Budget Constraints

Selecting informative data points for expert feedback can significantly ...

0 Aodong Li, et al. ∙

research

∙ 02/09/2023

Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes

Autoencoders and their variants are among the most widely used models in...

0 Ba-Hien Tran, et al. ∙

research

∙ 11/15/2022

Probabilistic Querying of Continuous-Time Event Sequences

Continuous-time event sequences, i.e., sequences consisting of continuou...

0 Alex Boyd, et al. ∙

research

∙ 10/12/2022

Predictive Querying for Autoregressive Neural Sequence Models

In reasoning about sequential events it is natural to pose probabilistic...

0 Alex Boyd, et al. ∙

research

∙ 09/14/2022

Lossy Image Compression with Conditional Diffusion Models

Denoising diffusion models have recently marked a milestone in high-qual...

6 Ruihan Yang, et al. ∙

research

∙ 05/27/2022

Raising the Bar in Graph-level Anomaly Detection

Graph-level anomaly detection has become a critical topic in diverse are...

0 Chen Qiu, et al. ∙

research

∙ 03/16/2022

SC2: Supervised Compression for Split Computing

Split computing distributes the execution of a neural network (e.g., for...

0 Yoshitomo Matsubara, et al. ∙

research

∙ 03/16/2022

Diffusion Probabilistic Modeling for Video Generation

Denoising diffusion probabilistic models are a promising new class of ge...

11 Ruihan Yang, et al. ∙

research

∙ 02/17/2022

Hybridizing Physical and Data-driven Prediction Methods for Physicochemical Properties

We present a generic way to hybridize physical and data-driven methods f...

0 Fabian Jirasek, et al. ∙

research

∙ 02/16/2022

Latent Outlier Exposure for Anomaly Detection with Contaminated Data

Anomaly detection aims at identifying data points that show systematic d...

0 Chen Qiu, et al. ∙

research

∙ 02/14/2022

An Introduction to Neural Data Compression

Neural compression is the application of neural networks and other machi...

0 Yibo Yang, et al. ∙

research

∙ 02/08/2022

Detecting Anomalies within Time Series using Local Neural Transformations

We develop a new method to detect anomalies within time series, which is...

0 Tim Schneider, et al. ∙

research

∙ 12/01/2021

Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEs

Understanding the details of small-scale convection and storm formation ...

0 Harshini Mangipudi, et al. ∙

research

∙ 11/23/2021

Towards Empirical Sandwich Bounds on the Rate-Distortion Function

Rate-distortion (R-D) function, a key quantity in information theory, ch...

0 Yibo Yang, et al. ∙

research

∙ 11/23/2021

Lossless Compression with Probabilistic Circuits

Despite extensive progress on image generation, deep generative models a...

0 Anji Liu, et al. ∙

research

∙ 08/21/2021

Supervised Compression for Resource-constrained Edge Computing Systems

There has been much interest in deploying deep learning algorithms on lo...

0 Yoshitomo Matsubara, et al. ∙

research

∙ 07/28/2021

Insights from Generative Modeling for Neural Video Compression

While recent machine learning research has revealed connections between ...

0 Ruihan Yang, et al. ∙

research

∙ 07/19/2021

Structured Stochastic Gradient MCMC

Stochastic gradient Markov chain Monte Carlo (SGMCMC) is considered the ...

0 Antonios Alexos, et al. ∙

research

∙ 03/30/2021

Neural Transformation Learning for Deep Anomaly Detection Beyond Images

Data transformations (e.g. rotations, reflections, and cropping) play an...

0 Chen Qiu, et al. ∙

research

∙ 12/15/2020

Variational Beam Search for Online Learning with Distribution Shifts

We consider the problem of online learning in the presence of sudden dis...

1 Aodong Li, et al. ∙

research

∙ 11/06/2020

User-Dependent Neural Sequence Models for Continuous-Time Event Data

Continuous-time event data are common in applications such as individual...

12 Alex Boyd, et al. ∙

research

∙ 10/26/2020

Scalable Gaussian Process Variational Autoencoders

Conventional variational autoencoders fail in modeling correlations betw...

18 Metod Jazbec, et al. ∙

research

∙ 10/20/2020

Variational Dynamic Mixtures

Deep probabilistic time series forecasting models have become an integra...

0 Chen Qiu, et al. ∙

research

∙ 10/19/2020

Hierarchical Autoregressive Modeling for Neural Video Compression

Recent work by Marino et al. (2020) showed improved performance in seque...

0 Ruihan Yang, et al. ∙

research

∙ 10/07/2020

Improving Sequential Latent Variable Models with Autoregressive Flows

We propose an approach for improving sequence modeling based on autoregr...

0 Joseph Marino, et al. ∙

research

∙ 07/03/2020

Generative Modeling for Atmospheric Convection

To improve climate modeling, we need a better understanding of multi-sca...

0 Griffin Mooers, et al. ∙

research

∙ 06/07/2020

Improving Inference for Neural Image Compression

We consider the problem of lossy image compression with deep latent vari...

19 Yibo Yang, et al. ∙

research

∙ 02/18/2020

Variable-Bitrate Neural Compression via Bayesian Arithmetic Coding

Deep Bayesian latent variable models have enabled new approaches to both...

14 Yibo Yang, et al. ∙

research

∙ 02/15/2020

Extreme Classification via Adversarial Softmax Approximation

Training a classifier over a large number of classes, known as 'extreme ...

20 Robert Bamler, et al. ∙

research

∙ 02/07/2020

The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks

Variational Bayesian Inference is a popular methodology for approximatin...

6 Jakub Świątkowski, et al. ∙

research

∙ 02/06/2020

How Good is the Bayes Posterior in Deep Neural Networks Really?

During the past five years the Bayesian deep learning community has deve...

27 Florian Wenzel, et al. ∙

research

∙ 01/29/2020

Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion

Activity coefficients, which are a measure of the non-ideality of liquid...

117 Fabian Jirasek, et al. ∙

research

∙ 01/14/2020

Hydra: Preserving Ensemble Diversity for Model Distillation

Ensembles of models have been empirically shown to improve predictive pe...

1 Linh Tran, et al. ∙

research

∙ 09/30/2019

Tightening Bounds for Variational Inference by Revisiting Perturbation Theory

Variational inference has become one of the most widely used methods in ...

19 Robert Bamler, et al. ∙

research

∙ 08/30/2019

Autoregressive Text Generation Beyond Feedback Loops

Autoregressive state transitions, where predictions are conditioned on p...

0 Florian Schmidt, et al. ∙

research

∙ 07/09/2019

Multivariate Time Series Imputation with Variational Autoencoders

Multivariate time series with missing values are common in many areas, f...

0 Vincent Fortuin, et al. ∙

research

∙ 07/04/2019

A Quantum Field Theory of Representation Learning

Continuous symmetries and their breaking play a prominent role in contem...

0 Robert Bamler, et al. ∙

research

∙ 07/01/2019

Augmenting and Tuning Knowledge Graph Embeddings

Knowledge graph embeddings rank among the most successful methods for li...

0 Robert Bamler, et al. ∙

research

∙ 10/05/2018

Deep Probabilistic Video Compression

We propose a variational inference approach to deep probabilistic video ...

0 Jun Han, et al. ∙

research

∙ 07/24/2018

Iterative Amortized Inference

Inference models are a key component in scaling variational inference to...

2 Joseph Marino, et al. ∙

research

∙ 07/04/2018

Quasi-Monte Carlo Variational Inference

Many machine learning problems involve Monte Carlo gradient estimators. ...

0 Alexander Buchholz, et al. ∙

research

∙ 04/08/2018

Active Mini-Batch Sampling using Repulsive Point Processes

The convergence speed of stochastic gradient descent (SGD) can be improv...

0 Cheng Zhang, et al. ∙

research

∙ 03/21/2018

Scalable Generalized Dynamic Topic Models

Dynamic topic models (DTMs) model the evolution of prevalent themes in l...

0 Patrick Jähnichen, et al. ∙

research

∙ 03/08/2018

Improving Optimization in Models With Continuous Symmetry Breaking

Many loss functions in representation learning are invariant under a con...

0 Robert Bamler, et al. ∙

Stephan Mandt

Featured Co-authors