34 citations · 162 across the 17 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
stat.ML2019★ 18 cited
Learning with minibatch Wasserstein : asymptotic and gradient properties
Kilian Fatras, Younes Zine, Rémi Flamary +2
Optimal transport distances are powerful tools to compare probability distributions and have found many applications in machine learning. Yet their algorithmic complexity prevents…
cs.LG2019★ 7 cited
Wasserstein Adversarial Regularization (WAR) on label noise
Kilian Fatras, Bharath Bhushan Damodaran, Sylvain Lobry +3
Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning ro…