Gauthier Gidel
Gauthier Gidel
Assistant professor at Mila, University of Montréal (DIRO)
Adresse e-mail validée de umontreal.ca - Page d'accueil
Titre
Citée par
Citée par
Année
A Variational Inequality Perspective on Generative Adversarial Networks
G Gidel, H Berard, G Vignoud, P Vincent, S Lacoste-Julien
ICLR 2019 - Proceedings of the Seventh International Conference on Learning …, 2019
1492019
Negative momentum for improved game dynamics
G Gidel, RA Hemmat, M Pezeshki, G Huang, R Lepriol, S Lacoste-Julien, ...
AISTATS 2019 - Proceedings of the 22nd International Conference on …, 2019
832019
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
S Vaswani, A Mishkin, I Laradji, M Schmidt, G Gidel, S Lacoste-Julien
NeurIPS 2019 - Advances in Neural Information Processing Systems, 2019
572019
Reducing noise in gan training with variance reduced extragradient
T Chavdarova, G Gidel, F Fleuret, S Lacoste-Julien
Neurips 2019 - Advances in Neural Information Processing Systems, 2019
552019
Frank-wolfe algorithms for saddle point problems
G Gidel, T Jebara, S Lacoste-Julien
AISTATS 2017 - Proceedings of the 20th International Conference on …, 2017
392017
A tight and unified analysis of gradient-based methods for a whole spectrum of differentiable games
W Azizian, I Mitliagkas, S Lacoste-Julien, G Gidel
International Conference on Artificial Intelligence and Statistics, 2863-2873, 2020
372020
Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks
G Gidel, F Bach, S Lacoste-Julien
NeurIPS 2019 - Advances in Neural Information Processing Systems, 3196-3206, 2019
372019
Finite regret and cycles with fixed step-size via alternating gradient descent-ascent
JP Bailey, G Gidel, G Piliouras
Conference on Learning Theory, 391-407, 2020
242020
Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics
G Kerg, K Goyette, MP Touzel, G Gidel, E Vorontsov, Y Bengio, G Lajoie
NeurIPS 2019 - Advances in Neural Information Processing Systems, 2019
242019
Frank-Wolfe Splitting via Augmented Lagrangian Method
G Gidel, F Pedregosa, S Lacoste-Julien
AISTATS 2018 - Proceedings of the 21st International Conference on …, 2018
222018
A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
H Berard, G Gidel, A Almahairi, P Vincent, S Lacoste-Julien
ICLR 2020 - Proceedings of the Eighth International Conference on Learning …, 2020
212020
Linear lower bounds and conditioning of differentiable games
A Ibrahim, W Azizian, G Gidel, I Mitliagkas
International Conference on Machine Learning, 4583-4593, 2020
19*2020
Accelerating Smooth Games by Manipulating Spectral Shapes
W Azizian, D Scieur, I Mitliagkas, S Lacoste-Julien, G Gidel
AISTATS 2020 - Proceedings of the 23rd International Conference on …, 2020
192020
Adaptive Three Operator Splitting
F Pedregosa, G Gidel
ICML 2018 - Proceedings of the 35rd International Conference on Machine Learning, 2018
142018
Parametric adversarial divergences are good task losses for generative modeling
G Huang, H Berard, A Touati, G Gidel, P Vincent, S Lacoste-Julien
arXiv preprint arXiv:1708.02511, 2017
92017
Real world games look like spinning tops
WM Czarnecki, G Gidel, B Tracey, K Tuyls, S Omidshafiei, D Balduzzi, ...
arXiv preprint arXiv:2004.09468, 2020
82020
Adversarial Example Games
AJ Bose, G Gidel, H Berrard, A Cianflone, P Vincent, S Lacoste-Julien, ...
arXiv preprint arXiv:2007.00720, 2020
32020
Minimax theorem for latent games or: How i learned to stop worrying about mixed-nash and love neural nets
G Gidel, D Balduzzi, WM Czarnecki, M Garnelo, Y Bachrach
arXiv preprint arXiv:2002.05820, 2020
22020
Parametric Adversarial Divergences are Good Task Losses for Generative Modeling. arXiv. org
G Huang, H Berard, A Touati, G Gidel, P Vincent, S Lacoste-Julien
August, 2017
22017
A single gradient step finds adversarial examples on random two-layers neural networks
S Bubeck, Y Cherapanamjeri, G Gidel, RT Combes
arXiv preprint arXiv:2104.03863, 2021
2021
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20