2 papers
cs.LG2021
When Are Solutions Connected in Deep Networks?
Quynh Nguyen, Pierre Brechet, Marco Mondelli
The question of how and why the phenomenon of mode connectivity occurs in training deep neural networks has gained remarkable attention in the research community. From a theoretica…
cs.LG2019
Informative GANs via Structured Regularization of Optimal Transport
Pierre Bréchet, Tao Wu, Thomas Möllenhoff +1
We tackle the challenge of disentangled representation learning in generative adversarial networks (GANs) from the perspective of regularized optimal transport (OT). Specifically,…