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 Roger Grosse

Don't Fix What ain't Broke: Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization


Feb 18, 2021
Guodong Zhang, Yuanhao Wang, Laurent Lessard, Roger Grosse


  Access Paper or Ask Questions

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning


Jan 15, 2021
Yuhuai Wu, Markus Rabe, Wenda Li, Jimmy Ba, Roger Grosse, Christian Szegedy

* 16 pages 

  Access Paper or Ask Questions

Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?


Nov 06, 2020
Chaoqi Wang, Shengyang Sun, Roger Grosse


  Access Paper or Ask Questions

Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians


Oct 26, 2020
Juhan Bae, Roger Grosse

* Published as a conference paper at Neurips 2020 

  Access Paper or Ask Questions

A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints


Oct 02, 2020
Guodong Zhang, Xuchan Bao, Laurent Lessard, Roger Grosse

* 36 pages 

  Access Paper or Ask Questions

Evaluating Lossy Compression Rates of Deep Generative Models


Aug 15, 2020
Sicong Huang, Alireza Makhzani, Yanshuai Cao, Roger Grosse


  Access Paper or Ask Questions

Regularized linear autoencoders recover the principal components, eventually


Jul 13, 2020
Xuchan Bao, James Lucas, Sushant Sachdeva, Roger Grosse


  Access Paper or Ask Questions

The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning


Jul 08, 2020
Yuhuai Wu, Honghua Dong, Roger Grosse, Jimmy Ba


  Access Paper or Ask Questions

Learning Branching Heuristics for Propositional Model Counting


Jul 07, 2020
Pashootan Vaezipoor, Gil Lederman, Yuhuai Wu, Chris J. Maddison, Roger Grosse, Edward Lee, Sanjit A. Seshia, Fahiem Bacchus


  Access Paper or Ask Questions

INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving


Jul 06, 2020
Yuhuai Wu, Albert Jiang, Jimmy Ba, Roger Grosse


  Access Paper or Ask Questions

When Does Preconditioning Help or Hurt Generalization?


Jul 02, 2020
Shun-ichi Amari, Jimmy Ba, Roger Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, Ji Xu

* 38 pages 

  Access Paper or Ask Questions

Understanding and mitigating exploding inverses in invertible neural networks


Jun 16, 2020
Jens Behrmann, Paul Vicol, Kuan-Chieh Wang, Roger Grosse, Jörn-Henrik Jacobsen


  Access Paper or Ask Questions

Picking Winning Tickets Before Training by Preserving Gradient Flow


Feb 18, 2020
Chaoqi Wang, Guodong Zhang, Roger Grosse

* In Proceedings of the 8th International Conference on Learning Representations (ICLR), 2020 
* Accepted at ICLR 2020 

  Access Paper or Ask Questions

Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks


Nov 09, 2019
Qiyang Li, Saminul Haque, Cem Anil, James Lucas, Roger Grosse, Jörn-Henrik Jacobsen

* 9 main pages, 31 pages total, 3 figures. Accepted at 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) 

  Access Paper or Ask Questions

Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse


Nov 06, 2019
James Lucas, George Tucker, Roger Grosse, Mohammad Norouzi

* 11 main pages, 10 appendix pages. 13 figures total. Accepted at 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) 

  Access Paper or Ask Questions

Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model


Jul 09, 2019
Guodong Zhang, Lala Li, Zachary Nado, James Martens, Sushant Sachdeva, George E. Dahl, Christopher J. Shallue, Roger Grosse


  Access Paper or Ask Questions

Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks


May 27, 2019
Guodong Zhang, James Martens, Roger Grosse


  Access Paper or Ask Questions

EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis


May 15, 2019
Chaoqi Wang, Roger Grosse, Sanja Fidler, Guodong Zhang

* ICML 2019 

  Access Paper or Ask Questions

Functional Variational Bayesian Neural Networks


Mar 14, 2019
Shengyang Sun, Guodong Zhang, Jiaxin Shi, Roger Grosse

* ICLR 2019 

  Access Paper or Ask Questions

Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions


Mar 07, 2019
Matthew MacKay, Paul Vicol, Jon Lorraine, David Duvenaud, Roger Grosse

* Published as a conference paper at ICLR 2019 

  Access Paper or Ask Questions

Eigenvalue Corrected Noisy Natural Gradient


Nov 30, 2018
Juhan Bae, Guodong Zhang, Roger Grosse


  Access Paper or Ask Questions

Sorting out Lipschitz function approximation


Nov 13, 2018
Cem Anil, James Lucas, Roger Grosse


  Access Paper or Ask Questions

Three Mechanisms of Weight Decay Regularization


Oct 29, 2018
Guodong Zhang, Chaoqi Wang, Bowen Xu, Roger Grosse


  Access Paper or Ask Questions

Reversible Recurrent Neural Networks


Oct 25, 2018
Matthew MacKay, Paul Vicol, Jimmy Ba, Roger Grosse

* Published as a conference paper at NIPS 2018 

  Access Paper or Ask Questions

Isolating Sources of Disentanglement in Variational Autoencoders


Oct 22, 2018
Ricky T. Q. Chen, Xuechen Li, Roger Grosse, David Duvenaud

* Added more experiments and improved clarity 

  Access Paper or Ask Questions

A Coordinate-Free Construction of Scalable Natural Gradient


Aug 30, 2018
Kevin Luk, Roger Grosse


  Access Paper or Ask Questions