NeurIPS 2021,  6 – 14 décembre 2021

Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm
Nathan Noiry, Flore Sentenac, Vianney Perchet

Sliced-Wasserstein Distance Using Concentration of Random Projections
Kimia Nadjahi, Alain Durmus, Pierre E. Jacob, Roland Badeau, Umut Şimşekli

Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks
Melih Barsbey, Milad Sefidgaran, Murat A. Erdogdu, Gaël Richard, Umut Şimşekli

Mixture weights optimisation for Alpha-Divergence Variational Inference
Kamélia Daudel, Randal Douc

A Framework to Learn with Interpretation
Jayneel Parekh, Pavlo Mozharovskyi, Florence d’Alché-Buc.