385 citations · 1.5k across the 64 of their papers we have counts for
5 papers · 1 filter
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…
Large scale Lasso with windowed active set for convolutional spike sorting
Laurent Dragoni, Rémi Flamary, Karim Lounici +1
Spike sorting is a fundamental preprocessing step in neuroscience that is central to access simultaneous but distinct neuronal activities and therefore to better understand the ani…
Concentration bounds for linear Monge mapping estimation and optimal transport domain adaptation
Rémi Flamary, Karim Lounici, André Ferrari
This article investigates the quality of the estimator of the linear Monge mapping between distributions. We provide the first concentration result on the linear mapping operator a…
Sliced Gromov-Wasserstein
Titouan Vayer, Rémi Flamary, Romain Tavenard +2
Recently used in various machine learning contexts, the Gromov-Wasserstein distance (GW) allows for comparing distributions whose supports do not necessarily lie in the same metric…
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…