Follow
Valentin Thomas
Valentin Thomas
PhD student, Mila, University of Montreal
Verified email at umontreal.ca - Homepage
Title
Cited by
Cited by
Year
Independently Controllable Factors
V Thomas*, J Pondard*, E Bengio*, M Sarfati, P Beaudoin, MJ Meurs, ...
arXiv preprint arXiv:1708.01289, 2017
912017
Disentangling the independently controllable factors of variation by interacting with the world
V Thomas, E Bengio, W Fedus, J Pondard, P Beaudoin, H Larochelle, ...
NIPS 2017 workshop on Learning Disentangled Representations: from …, 2018
612018
On the interplay between noise and curvature and its effect on optimization and generalization
V Thomas, F Pedregosa, B Merriënboer, PA Manzagol, Y Bengio, ...
International Conference on Artificial Intelligence and Statistics, 3503-3513, 2020
542020
Probabilistic Planning with Sequential Monte Carlo methods
V Thomas*, A Piché*, C Ibrahim, Y Bengio, C Pal
ICLR, https://openreview.net/pdf?id=ByetGn0cYX, 2019
45*2019
Independently Controllable Features
E Bengio, V Thomas, J Pineau, D Precup, Y Bengio
RLDM 2017, 2017
452017
Beyond variance reduction: Understanding the true impact of baselines on policy optimization
V Thomas*, W Chung*, MC Machado, N Le Roux
International Conference on Machine Learning, 1999-2009, 2021
272021
Decoupling Backpropagation using Constrained Optimization Methods
A Gotmare*, V Thomas*, J Brea, M Jaggi
ICML 2018 workshop on Efficient Credit Assignment, 2018
172018
Information matrices and generalization
V Thomas, F Pedregosa, B van Merriënboer, PA Mangazol, Y Bengio, ...
arXiv preprint arXiv:1906.07774, 2019
142019
Beyond Target Networks: Improving Deep -learning with Functional Regularization
A Piché*, V Thomas*, J Marino, GM Marconi, C Pal, ME Khan
arXiv preprint arXiv:2106.02613, 2021
112021
The Role of Baselines in Policy Gradient Optimization
J Mei, W Chung, V Thomas, B Dai, C Szepesvari, D Schuurmans
Advances in Neural Information Processing Systems 35, 17818-17830, 2022
62022
On the role of overparameterization in off-policy Temporal Difference learning with linear function approximation
V Thomas
NeurIPS, https://openreview.net/forum?id=g-H3oNAR, 2022
32022
Contrôle de l’intrication de deux Qubits
V Thomas
Planning with Latent Simulated Trajectories
A Piché1, V Thomas12, C Ibrahim, J Cornebise, C Pal
The system can't perform the operation now. Try again later.
Articles 1–13