Timezone: »
Recent literature has demonstrated promising results for training Generative Adversarial Networks by employing a set of discriminators, in contrast to the traditional game involving one generator against a single adversary. Such methods perform single-objective optimization on some simple consolidation of the losses, e.g. an arithmetic average. In this work, we revisit the multiple-discriminator setting by framing the simultaneous minimization of losses provided by different models as a multi-objective optimization problem. Specifically, we evaluate the performance of multiple gradient descent and the hypervolume maximization algorithm on a number of different datasets. Moreover, we argue that the previously proposed methods and hypervolume maximization can all be seen as variations of multiple gradient descent in which the update direction can be computed efficiently. Our results indicate that hypervolume maximization presents a better compromise between sample quality and computational cost than previous methods.
Author Information
Isabela Albuquerque (Institut National de la Recherche Scientifique)
Joao Monteiro (Institut National de la Recherche Scientifique (INRS))
Thang Doan (McGill University)
Breandan Considine (Mila)
Tiago Falk (INRS-EMT)
Ioannis Mitliagkas (MILA, UdeM)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Oral: Multi-objective training of Generative Adversarial Networks with multiple discriminators »
Thu. Jun 13th 04:30 -- 04:35 PM Room Hall A
More from the Same Authors
-
2022 : Building a Subspace of Policies for Scalable Continual Learning »
Jean-Baptiste Gaya · Thang Doan · Lucas Caccia · Laure Soulier · Ludovic Denoyer · Roberta Raileanu -
2023 Poster: Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning »
Sébastien Lachapelle · Tristan Deleu · Divyat Mahajan · Ioannis Mitliagkas · Yoshua Bengio · Simon Lacoste-Julien · Quentin Bertrand -
2021 Workshop: Theory and Foundation of Continual Learning »
Thang Doan · Bogdan Mazoure · Amal Rannen Triki · Rahaf Aljundi · Vincenzo Lomonaco · Xu He · Arslan Chaudhry -
2020 Poster: Stochastic Hamiltonian Gradient Methods for Smooth Games »
Nicolas Loizou · Hugo Berard · Alexia Jolicoeur-Martineau · Pascal Vincent · Simon Lacoste-Julien · Ioannis Mitliagkas -
2020 Poster: Linear Lower Bounds and Conditioning of Differentiable Games »
Adam Ibrahim · Waïss Azizian · Gauthier Gidel · Ioannis Mitliagkas -
2020 Poster: An end-to-end approach for the verification problem: learning the right distance »
Joao Monteiro · Isabela Albuquerque · Jahangir Alam · R Devon Hjelm · Tiago Falk -
2019 Poster: State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations »
Alex Lamb · Jonathan Binas · Anirudh Goyal · Sandeep Subramanian · Ioannis Mitliagkas · Yoshua Bengio · Michael Mozer -
2019 Oral: State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations »
Alex Lamb · Jonathan Binas · Anirudh Goyal · Sandeep Subramanian · Ioannis Mitliagkas · Yoshua Bengio · Michael Mozer -
2018 Poster: Learning Representations and Generative Models for 3D Point Clouds »
Panagiotis Achlioptas · Olga Diamanti · Ioannis Mitliagkas · Leonidas Guibas -
2018 Oral: Learning Representations and Generative Models for 3D Point Clouds »
Panagiotis Achlioptas · Olga Diamanti · Ioannis Mitliagkas · Leonidas Guibas