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 Sebastian Nowozin

TaskNorm: Rethinking Batch Normalization for Meta-Learning


Mar 06, 2020
John Bronskill, Jonathan Gordon, James Requeima, Sebastian Nowozin, Richard E. Turner


  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 ÅšwiÄ…tkowski, Linh Tran, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton, Sebastian Nowozin


  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

Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations


Sep 05, 2019
Jan Stühmer, Richard E. Turner, Sebastian Nowozin


  Access Paper or Ask Questions

Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model


Aug 14, 2019
Wenbo Gong, Sebastian Tschiatschek, Richard Turner, Sebastian Nowozin, José Miguel Hernández-Lobato, Cheng Zhang


  Access Paper or Ask Questions

Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes


Jun 18, 2019
James Requeima, Jonathan Gordon, John Bronskill, Sebastian Nowozin, Richard E. Turner


  Access Paper or Ask Questions

Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift


Jun 06, 2019
Yaniv Ovadia, Emily Fertig, Jie Ren, Zachary Nado, D Sculley, Sebastian Nowozin, Joshua V. Dillon, Balaji Lakshminarayanan, Jasper Snoek


  Access Paper or Ask Questions

Occupancy Networks: Learning 3D Reconstruction in Function Space


Dec 10, 2018
Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, Andreas Geiger


  Access Paper or Ask Questions

Contextual Face Recognition with a Nested-Hierarchical Nonparametric Identity Model


Nov 19, 2018
Daniel C. Castro, Sebastian Nowozin

* NeurIPS 2018 Workshop on All of Bayesian Nonparametrics ([email protected] 2018). arXiv admin note: substantial text overlap with arXiv:1807.07872 

  Access Paper or Ask Questions

EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE


Oct 12, 2018
Chao Ma, Sebastian Tschiatschek, Konstantina Palla, José Miguel Hernández-Lobato, Sebastian Nowozin, Cheng Zhang


  Access Paper or Ask Questions

Fixing Variational Bayes: Deterministic Variational Inference for Bayesian Neural Networks


Oct 09, 2018
Anqi Wu, Sebastian Nowozin, Edward Meeds, Richard E. Turner, José Miguel Hernández-Lobato, Alexander L. Gaunt

* 9 pages, 5 figures 

  Access Paper or Ask Questions

Which Training Methods for GANs do actually Converge?


Jul 31, 2018
Lars Mescheder, Andreas Geiger, Sebastian Nowozin

* International Conference on Machine Learning 2018 
* conference 

  Access Paper or Ask Questions

From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data


Jul 20, 2018
Daniel C. Castro, Sebastian Nowozin

* Accepted for publication at ECCV 2018 

  Access Paper or Ask Questions

The Numerics of GANs


Jun 11, 2018
Lars Mescheder, Sebastian Nowozin, Andreas Geiger


  Access Paper or Ask Questions

Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks


Jun 11, 2018
Lars Mescheder, Sebastian Nowozin, Andreas Geiger


  Access Paper or Ask Questions

Decision-Theoretic Meta-Learning: Versatile and Efficient Amortization of Few-Shot Learning


May 31, 2018
Jonathan Gordon, John Bronskill, Matthias Bauer, Sebastian Nowozin, Richard E. Turner


  Access Paper or Ask Questions

Adversarially Robust Training through Structured Gradient Regularization


May 22, 2018
Kevin Roth, Aurelien Lucchi, Sebastian Nowozin, Thomas Hofmann


  Access Paper or Ask Questions

PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples


May 21, 2018
Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman

* ICLR 2018 

  Access Paper or Ask Questions

Deep Directional Statistics: Pose Estimation with Uncertainty Quantification


May 09, 2018
Sergey Prokudin, Peter Gehler, Sebastian Nowozin


  Access Paper or Ask Questions

DSAC - Differentiable RANSAC for Camera Localization


Mar 21, 2018
Eric Brachmann, Alexander Krull, Sebastian Nowozin, Jamie Shotton, Frank Michel, Stefan Gumhold, Carsten Rother

* CVPR 2017 

  Access Paper or Ask Questions

Hybrid VAE: Improving Deep Generative Models using Partial Observations


Nov 30, 2017
Sergey Tulyakov, Andrew Fitzgibbon, Sebastian Nowozin


  Access Paper or Ask Questions

Stabilizing Training of Generative Adversarial Networks through Regularization


Nov 07, 2017
Kevin Roth, Aurelien Lucchi, Sebastian Nowozin, Thomas Hofmann


  Access Paper or Ask Questions

The Atari Grand Challenge Dataset


May 31, 2017
Vitaly Kurin, Sebastian Nowozin, Katja Hofmann, Lucas Beyer, Bastian Leibe


  Access Paper or Ask Questions

Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations


May 24, 2017
Diane Bouchacourt, Ryota Tomioka, Sebastian Nowozin


  Access Paper or Ask Questions

PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning


Apr 11, 2017
Alexander Krull, Eric Brachmann, Sebastian Nowozin, Frank Michel, Jamie Shotton, Carsten Rother


  Access Paper or Ask Questions

DeepCoder: Learning to Write Programs


Mar 08, 2017
Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, Daniel Tarlow

* Submitted to ICLR 2017 

  Access Paper or Ask Questions

Memory Lens: How Much Memory Does an Agent Use?


Nov 21, 2016
Christoph Dann, Katja Hofmann, Sebastian Nowozin

* Presented at NIPS 2016 Workshop on Interpretable Machine Learning in Complex Systems 

  Access Paper or Ask Questions

Probabilistic Duality for Parallel Gibbs Sampling without Graph Coloring


Nov 21, 2016
Lars Mescheder, Sebastian Nowozin, Andreas Geiger


  Access Paper or Ask Questions

DISCO Nets: DISsimilarity COefficient Networks


Oct 28, 2016
Diane Bouchacourt, M. Pawan Kumar, Sebastian Nowozin


  Access Paper or Ask Questions