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 Gauthier Gidel

Gauthier Gidel

A single gradient step finds adversarial examples on random two-layers neural networks


Apr 09, 2021
Sébastien Bubeck, Yeshwanth Cherapanamjeri, Gauthier Gidel, Rémi Tachet des Combes

* Added a comment about universal adversarial perturbations. 18 pages, 7 figures 
  Access Paper or Ask Questions

Online Adversarial Attacks


Mar 02, 2021
Andjela Mladenovic, Avishek Joey Bose, Hugo Berard, William L. Hamilton, Simon Lacoste-Julien, Pascal Vincent, Gauthier Gidel

Figure 1 for Online Adversarial Attacks
Figure 2 for Online Adversarial Attacks
Figure 3 for Online Adversarial Attacks
Figure 4 for Online Adversarial Attacks
* Preprint 
  Access Paper or Ask Questions

Adversarial Example Games


Jul 01, 2020
Avishek Joey Bose, Gauthier Gidel, Hugo Berrard, Andre Cianflone, Pascal Vincent, Simon Lacoste-Julien, William L. Hamilton

Figure 1 for Adversarial Example Games
Figure 2 for Adversarial Example Games
Figure 3 for Adversarial Example Games
Figure 4 for Adversarial Example Games

  Access Paper or Ask Questions

Real World Games Look Like Spinning Tops


Apr 20, 2020
Wojciech Marian Czarnecki, Gauthier Gidel, Brendan Tracey, Karl Tuyls, Shayegan Omidshafiei, David Balduzzi, Max Jaderberg

Figure 1 for Real World Games Look Like Spinning Tops
Figure 2 for Real World Games Look Like Spinning Tops
Figure 3 for Real World Games Look Like Spinning Tops
Figure 4 for Real World Games Look Like Spinning Tops

  Access Paper or Ask Questions

Minimax Theorem for Latent Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets


Feb 14, 2020
Gauthier Gidel, David Balduzzi, Wojciech Marian Czarnecki, Marta Garnelo, Yoram Bachrach

Figure 1 for Minimax Theorem for Latent Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets
Figure 2 for Minimax Theorem for Latent Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets
Figure 3 for Minimax Theorem for Latent Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets
* 15 pages 
  Access Paper or Ask Questions

Accelerating Smooth Games by Manipulating Spectral Shapes


Jan 02, 2020
Waïss Azizian, Damien Scieur, Ioannis Mitliagkas, Simon Lacoste-Julien, Gauthier Gidel

Figure 1 for Accelerating Smooth Games by Manipulating Spectral Shapes
Figure 2 for Accelerating Smooth Games by Manipulating Spectral Shapes
Figure 3 for Accelerating Smooth Games by Manipulating Spectral Shapes

  Access Paper or Ask Questions

A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable Games


Jun 24, 2019
Waïss Azizian, Ioannis Mitliagkas, Simon Lacoste-Julien, Gauthier Gidel

Figure 1 for A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable Games
Figure 2 for A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable Games

  Access Paper or Ask Questions

Lower Bounds and Conditioning of Differentiable Games


Jun 17, 2019
Adam Ibrahim, Waïss Azizian, Gauthier Gidel, Ioannis Mitliagkas

Figure 1 for Lower Bounds and Conditioning of Differentiable Games
Figure 2 for Lower Bounds and Conditioning of Differentiable Games
Figure 3 for Lower Bounds and Conditioning of Differentiable Games
Figure 4 for Lower Bounds and Conditioning of Differentiable Games
* Submitted to NeurIPS 2019 
  Access Paper or Ask Questions

A Closer Look at the Optimization Landscapes of Generative Adversarial Networks


Jun 11, 2019
Hugo Berard, Gauthier Gidel, Amjad Almahairi, Pascal Vincent, Simon Lacoste-Julien

Figure 1 for A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
Figure 2 for A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
Figure 3 for A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
Figure 4 for A Closer Look at the Optimization Landscapes of Generative Adversarial Networks

  Access Paper or Ask Questions

Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics


May 28, 2019
Giancarlo Kerg, Kyle Goyette, Maximilian Puelma Touzel, Gauthier Gidel, Eugene Vorontsov, Yoshua Bengio, Guillaume Lajoie

Figure 1 for Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics
Figure 2 for Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics
Figure 3 for Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics
Figure 4 for Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics

  Access Paper or Ask Questions

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates


May 24, 2019
Sharan Vaswani, Aaron Mishkin, Issam Laradji, Mark Schmidt, Gauthier Gidel, Simon Lacoste-Julien

Figure 1 for Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
Figure 2 for Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
Figure 3 for Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
Figure 4 for Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates

  Access Paper or Ask Questions

Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks


Apr 30, 2019
Gauthier Gidel, Francis Bach, Simon Lacoste-Julien

Figure 1 for Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks
Figure 2 for Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks
Figure 3 for Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks
* 25 pages 
  Access Paper or Ask Questions

Reducing Noise in GAN Training with Variance Reduced Extragradient


Apr 18, 2019
Tatjana Chavdarova, Gauthier Gidel, François Fleuret, Simon Lacoste-Julien

Figure 1 for Reducing Noise in GAN Training with Variance Reduced Extragradient
Figure 2 for Reducing Noise in GAN Training with Variance Reduced Extragradient
Figure 3 for Reducing Noise in GAN Training with Variance Reduced Extragradient
Figure 4 for Reducing Noise in GAN Training with Variance Reduced Extragradient

  Access Paper or Ask Questions

A Variational Inequality Perspective on Generative Adversarial Networks


Nov 02, 2018
Gauthier Gidel, Hugo Berard, Gaëtan Vignoud, Pascal Vincent, Simon Lacoste-Julien

Figure 1 for A Variational Inequality Perspective on Generative Adversarial Networks
Figure 2 for A Variational Inequality Perspective on Generative Adversarial Networks
Figure 3 for A Variational Inequality Perspective on Generative Adversarial Networks
Figure 4 for A Variational Inequality Perspective on Generative Adversarial Networks
* 33 pages 
  Access Paper or Ask Questions

Adaptive Three Operator Splitting


Jul 31, 2018
Fabian Pedregosa, Gauthier Gidel

Figure 1 for Adaptive Three Operator Splitting
Figure 2 for Adaptive Three Operator Splitting
Figure 3 for Adaptive Three Operator Splitting
Figure 4 for Adaptive Three Operator Splitting
* Proceedings of the 35th International Conference on Machine Learning, PMLR 80:4082-4091, 2018 
  Access Paper or Ask Questions

Negative Momentum for Improved Game Dynamics


Jul 12, 2018
Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki, Gabriel Huang, Remi Lepriol, Simon Lacoste-Julien, Ioannis Mitliagkas

Figure 1 for Negative Momentum for Improved Game Dynamics
Figure 2 for Negative Momentum for Improved Game Dynamics
Figure 3 for Negative Momentum for Improved Game Dynamics
Figure 4 for Negative Momentum for Improved Game Dynamics

  Access Paper or Ask Questions

Parametric Adversarial Divergences are Good Task Losses for Generative Modeling


Jun 27, 2018
Gabriel Huang, Hugo Berard, Ahmed Touati, Gauthier Gidel, Pascal Vincent, Simon Lacoste-Julien

Figure 1 for Parametric Adversarial Divergences are Good Task Losses for Generative Modeling
Figure 2 for Parametric Adversarial Divergences are Good Task Losses for Generative Modeling
Figure 3 for Parametric Adversarial Divergences are Good Task Losses for Generative Modeling
Figure 4 for Parametric Adversarial Divergences are Good Task Losses for Generative Modeling
* 22 pages 
  Access Paper or Ask Questions

Frank-Wolfe Splitting via Augmented Lagrangian Method


Apr 09, 2018
Gauthier Gidel, Fabian Pedregosa, Simon Lacoste-Julien

Figure 1 for Frank-Wolfe Splitting via Augmented Lagrangian Method
Figure 2 for Frank-Wolfe Splitting via Augmented Lagrangian Method
* Appears in: Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018). 30 pages 
  Access Paper or Ask Questions

Frank-Wolfe Algorithms for Saddle Point Problems


Mar 03, 2017
Gauthier Gidel, Tony Jebara, Simon Lacoste-Julien

Figure 1 for Frank-Wolfe Algorithms for Saddle Point Problems
* Appears in: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017). 39 pages 
  Access Paper or Ask Questions