17 citations · 57 across the 16 of their papers we have counts for
6 papers · 1 filter
Optimal 1-Wasserstein Distance for WGANs
Arthur Stéphanovitch, Ugo Tanielian, Benoît Cadre +2
The mathematical forces at work behind Generative Adversarial Networks raise challenging theoretical issues. Motivated by the important question of characterizing the geometrical p…
Approximating Lipschitz continuous functions with GroupSort neural networks
Ugo Tanielian, Maxime Sangnier, Gerard Biau
Recent advances in adversarial attacks and Wasserstein GANs have advocated for use of neural networks with restricted Lipschitz constants. Motivated by these observations, we study…
Learning disconnected manifolds: a no GANs land
Ugo Tanielian, Thibaut Issenhuth, Elvis Dohmatob +1
Typical architectures of Generative AdversarialNetworks make use of a unimodal latent distribution transformed by a continuous generator. Consequently, the modeled distribution alw…
Relaxed Softmax for learning from Positive and Unlabeled data
Ugo Tanielian, Flavian Vasile
In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss…
Distributionally Robust Counterfactual Risk Minimization
Louis Faury, Ugo Tanielian, Flavian Vasile +2
This manuscript introduces the idea of using Distributionally Robust Optimization (DRO) for the Counterfactual Risk Minimization (CRM) problem. Tapping into a rich existing literat…
Some Theoretical Properties of GANs
G. Biau, B. Cadre, M. Sangnier +1
Generative Adversarial Networks (GANs) are a class of generative algorithms that have been shown to produce state-of-the art samples, especially in the domain of image creation. Th…