Gauthier Gidel

is this you? claim profile

0 followers
Université de Montréal

Reducing Noise in GAN Training with Variance Reduced Extragradient

Using large mini-batches when training generative adversarial networks (...
04/18/2019 ∙ by Tatjana Chavdarova, et al. ∙ 38 ∙ share

read it
Accelerating Smooth Games by Manipulating Spectral Shapes

We use matrix iteration theory to characterize acceleration in smooth ga...
01/02/2020 ∙ by Waïss Azizian, et al. ∙ 16 ∙ share

read it
Negative Momentum for Improved Game Dynamics

Games generalize the optimization paradigm by introducing different obje...
07/12/2018 ∙ by Gauthier Gidel, et al. ∙ 10 ∙ share

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

Recent works have shown that stochastic gradient descent (SGD) achieves ...
05/24/2019 ∙ by Sharan Vaswani, et al. ∙ 10 ∙ share

read it
Real World Games Look Like Spinning Tops

This paper investigates the geometrical properties of real world games (...
04/20/2020 ∙ by Wojciech Marian Czarnecki, et al. ∙ 10 ∙ share

read it
Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks

When optimizing over-parameterized models, such as deep neural networks,...
04/30/2019 ∙ by Gauthier Gidel, et al. ∙ 2 ∙ share

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

A recent strategy to circumvent the exploding and vanishing gradient pro...
05/28/2019 ∙ by Giancarlo Kerg, et al. ∙ 1 ∙ share

read it
A Closer Look at the Optimization Landscapes of Generative Adversarial Networks

Generative adversarial networks have been very successful in generative ...
06/11/2019 ∙ by Hugo Berard, et al. ∙ 1 ∙ share

read it
Parametric Adversarial Divergences are Good Task Losses for Generative Modeling

Generative modeling of high dimensional data like images is a notoriousl...
08/08/2017 ∙ by Gabriel Huang, et al. ∙ 0 ∙ share

read it
Frank-Wolfe Algorithms for Saddle Point Problems

We extend the Frank-Wolfe (FW) optimization algorithm to solve constrain...
10/25/2016 ∙ by Gauthier Gidel, et al. ∙ 0 ∙ share

read it
A Variational Inequality Perspective on Generative Adversarial Nets

Stability has been a recurrent issue in training generative adversarial ...
02/28/2018 ∙ by Gauthier Gidel, et al. ∙ 0 ∙ share

read it
Adaptive Three Operator Splitting

We propose and analyze a novel adaptive step size variant of the Davis-Y...
04/06/2018 ∙ by Fabian Pedregosa, et al. ∙ 0 ∙ share

read it
Frank-Wolfe Splitting via Augmented Lagrangian Method

Minimizing a function over an intersection of convex sets is an importan...
04/09/2018 ∙ by Gauthier Gidel, et al. ∙ 0 ∙ share

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

We consider differentiable games: multi-objective minimization problems,...
06/13/2019 ∙ by Waïss Azizian, et al. ∙ 0 ∙ share

read it
Lower Bounds and Conditioning of Differentiable Games

Many recent machine learning tools rely on differentiable game formulati...
06/17/2019 ∙ by Adam Ibrahim, et al. ∙ 0 ∙ share

read it
Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent

Gradient descent is arguably one of the most popular online optimization...
07/09/2019 ∙ by James P. Bailey, et al. ∙ 0 ∙ share

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

Adversarial training, a special case of multi-objective optimization, is...
02/14/2020 ∙ by Gauthier Gidel, et al. ∙ 0 ∙ share

read it

Gauthier Gidel

Featured Co-authors

Yoshua Bengio

Francis Bach

Simon Lacoste-Julien

Pascal Vincent

Mark Schmidt

Karl Tuyls

David Balduzzi

Georgios Piliouras

Ioannis Mitliagkas

François Fleuret

Max Jaderberg

Reducing Noise in GAN Training with Variance Reduced Extragradient

Accelerating Smooth Games by Manipulating Spectral Shapes

Negative Momentum for Improved Game Dynamics

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

Real World Games Look Like Spinning Tops

Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks

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

A Closer Look at the Optimization Landscapes of Generative Adversarial Networks

Parametric Adversarial Divergences are Good Task Losses for Generative Modeling

Frank-Wolfe Algorithms for Saddle Point Problems

A Variational Inequality Perspective on Generative Adversarial Nets

Adaptive Three Operator Splitting

Frank-Wolfe Splitting via Augmented Lagrangian Method

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

Lower Bounds and Conditioning of Differentiable Games

Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent

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