Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Stephan Mandt

Supervised Compression for Resource-constrained Edge Computing Systems


Aug 21, 2021
Yoshitomo Matsubara, Ruihan Yang, Marco Levorato, Stephan Mandt

* Preprint 

  Access Paper or Ask Questions

Insights from Generative Modeling for Neural Video Compression


Jul 28, 2021
Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt

* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. arXiv admin note: text overlap with arXiv:2010.10258 

  Access Paper or Ask Questions

Structured Stochastic Gradient MCMC


Jul 19, 2021
Antonios Alexos, Alex Boyd, Stephan Mandt


  Access Paper or Ask Questions

Neural Transformation Learning for Deep Anomaly Detection Beyond Images


Mar 31, 2021
Chen Qiu, Timo Pfrommer, Marius Kloft, Stephan Mandt, Maja Rudolph


  Access Paper or Ask Questions

Variational Beam Search for Online Learning with Distribution Shifts


Dec 15, 2020
Aodong Li, Alex Boyd, Padhraic Smyth, Stephan Mandt


  Access Paper or Ask Questions

Scalable Gaussian Process Variational Autoencoders


Nov 12, 2020
Metod Jazbec, Vincent Fortuin, Michael Pearce, Stephan Mandt, Gunnar Rätsch


  Access Paper or Ask Questions

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


Nov 06, 2020
Alex Boyd, Robert Bamler, Stephan Mandt, Padhraic Smyth

* Accepted at NeurIPS 2020 

  Access Paper or Ask Questions

Variational Dynamic Mixtures


Oct 20, 2020
Chen Qiu, Stephan Mandt, Maja Rudolph


  Access Paper or Ask Questions

Hierarchical Autoregressive Modeling for Neural Video Compression


Oct 19, 2020
Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt


  Access Paper or Ask Questions

Improving Sequential Latent Variable Models with Autoregressive Flows


Oct 07, 2020
Joseph Marino, Lei Chen, Jiawei He, Stephan Mandt


  Access Paper or Ask Questions

Generative Modeling for Atmospheric Convection


Jul 03, 2020
Griffin Mooers, Jens Tuyls, Stephan Mandt, Michael Pritchard, Tom Beucler

* 8 Pages, 6 Figures. Submitted to Climate Informatics 2020 

  Access Paper or Ask Questions

Improving Inference for Neural Image Compression


Jun 09, 2020
Yibo Yang, Robert Bamler, Stephan Mandt

* 8 pages + detailed supplement with additional qualitative and quantitative results 

  Access Paper or Ask Questions

Variable-Bitrate Neural Compression via Bayesian Arithmetic Coding


Feb 18, 2020
Yibo Yang, Robert Bamler, Stephan Mandt

* 8 pages + detailed supplement with additional full resolution reconstructed images 

  Access Paper or Ask Questions

Extreme Classification via Adversarial Softmax Approximation


Feb 15, 2020
Robert Bamler, Stephan Mandt

* Accepted for presentation at the Eighth International Conference on Learning Representations (ICLR 2020), https://openreview.net/forum?id=rJxe3xSYDS 

  Access Paper or Ask Questions

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


Feb 07, 2020
Jakub Swiatkowski, Kevin Roth, Bastiaan S. Veeling, Linh Tran, Joshua V. Dillon, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton, Sebastian Nowozin


  Access Paper or Ask Questions

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


Feb 06, 2020
Florian Wenzel, Kevin Roth, Bastiaan S. Veeling, Jakub Świątkowski, Linh Tran, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton, Sebastian Nowozin


  Access Paper or Ask Questions

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


Jan 29, 2020
Fabian Jirasek, Rodrigo A. S. Alves, Julie Damay, Robert A. Vandermeulen, Robert Bamler, Michael Bortz, Stephan Mandt, Marius Kloft, Hans Hasse

* J. Phys. Chem. Lett. 11 (2020) 981-985 
* Published version: J. Phys. Chem. Lett. 11 (2020) 981-985; https://pubs.acs.org/doi/full/10.1021/acs.jpclett.9b03657 

  Access Paper or Ask Questions

Hydra: Preserving Ensemble Diversity for Model Distillation


Jan 14, 2020
Linh Tran, Bastiaan S. Veeling, Kevin Roth, Jakub Swiatkowski, Joshua V. Dillon, Jasper Snoek, Stephan Mandt, Tim Salimans, Sebastian Nowozin, Rodolphe Jenatton


  Access Paper or Ask Questions

Tightening Bounds for Variational Inference by Revisiting Perturbation Theory


Sep 30, 2019
Robert Bamler, Cheng Zhang, Manfred Opper, Stephan Mandt

* To appear in Journal of Statistical Mechanics: Theory and Experiment (JSTAT), 2019 

  Access Paper or Ask Questions

Autoregressive Text Generation Beyond Feedback Loops


Aug 30, 2019
Florian Schmidt, Stephan Mandt, Thomas Hofmann

* emnlp camera ready 

  Access Paper or Ask Questions

Multivariate Time Series Imputation with Variational Autoencoders


Jul 12, 2019
Vincent Fortuin, Gunnar Rätsch, Stephan Mandt


  Access Paper or Ask Questions

A Quantum Field Theory of Representation Learning


Jul 04, 2019
Robert Bamler, Stephan Mandt

* Presented at the ICML 2019 Workshop on Theoretical Physics for Deep Learning 

  Access Paper or Ask Questions

Augmenting and Tuning Knowledge Graph Embeddings


Jul 01, 2019
Robert Bamler, Farnood Salehi, Stephan Mandt

* Published version, Conference on Uncertainty in Artificial Intelligence (UAI 2019) 

  Access Paper or Ask Questions

Advances in Variational Inference


Oct 23, 2018
Cheng Zhang, Judith Butepage, Hedvig Kjellstrom, Stephan Mandt


  Access Paper or Ask Questions

Improving Optimization for Models With Continuous Symmetry Breaking


Jul 30, 2018
Robert Bamler, Stephan Mandt

* In the proceedings of International Conference on Machine Learning (ICML 2018) 

  Access Paper or Ask Questions

Iterative Amortized Inference


Jul 24, 2018
Joseph Marino, Yisong Yue, Stephan Mandt

* International Conference on Machine Learning (ICML) 2018 

  Access Paper or Ask Questions

Quasi-Monte Carlo Variational Inference


Jul 04, 2018
Alexander Buchholz, Florian Wenzel, Stephan Mandt

* Published in the proceedings of the 35th International Conference on Machine Learning (ICML 2018) 

  Access Paper or Ask Questions