Program Highlights »
Workshop
Sat Dec 9th 08:00 AM -- 06:30 PM @ 102 A+B
Optimal Transport and Machine Learning
Olivier Bousquet · Marco Cuturi · Gabriel Peyré · Fei Sha · Justin Solomon





Workshop Home Page

Optimal transport (OT) is gradually establishing itself as a powerful and essential tool to compare probability measures, which in machine learning take the form of point clouds, histograms, bags-of-features, or more generally datasets to be compared with probability densities and generative models. OT can be traced back to early work by Monge, and later to Kantorovich and Dantzig during the birth of linear programming. The mathematical theory of OT has produced several important developments since the 90's, crowned by Cédric Villani's Fields Medal in 2010. OT is now transitioning into more applied spheres, including recent applications to machine learning, because it can tackle challenging learning scenarios including dimensionality reduction, structured prediction problems that involve histograms, and estimation of generative models in highly degenerate, high-dimensional problems. This workshop will follow that organized 3 years ago (NIPS 2014) and will seek to amplify that trend. We will provide the audience with an update on all of the very recent successes brought forward by efficient solvers and innovative applications through a long list of invited talks. We will add to that a few contributed presentations (oral, and, if needed posters) and, finally, a panel for all invited speakers to take questions from the audience and formulate more nuanced opinions on this nascent field.

08:00 AM Structured Optimal Transport (with T. Jaakkola, S. Jegelka)
David Alvarez Melis
08:20 AM Approximate Bayesian computation with the Wasserstein distance
Pierre E Jacob
09:00 AM Gradient flow in the Wasserstein metric
Katy Craig
09:40 AM Approximate inference with Wasserstein gradient flows (with T. Poggio)
Charlie Frogner
10:00 AM 6 x 3 minutes spotlights
Rémi Flamary, Yongxin Chen, Napat Rujeerapaiboon, Jonas Adler, John Lee, Lucas R Roberts
11:00 AM Wasserstein embeddings (tba)
Alexandr Andoni
11:40 AM Laplacian operator and Brownian motions on the Wasserstein space
Wilfrid Gangbo
01:40 PM Geometrical Insights for Unsupervised Learning
Leon Bottou
02:20 PM Improving GANs Using Optimal Transport (with H. Zhang, A. Radford, D. Metaxas)
Tim Salimans
02:40 PM Overrelaxed Sinkhorn-Knopp Algorithm for Regularized Optimal Transport (with L. Chizat, C. Dossal, N. Papadakis)
Alexis THIBAULT
03:30 PM Domain adaptation with optimal transport : from mapping to learning with joint distribution
Rémi Flamary
04:10 PM Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
Francis Bach
04:50 PM 7 x 3 minutes spotlights
Elsa Cazelles, Aude Genevay, gomena Mena, Christoph Brauer, Asja Fischer, Henning Petzka, Vivien Seguy, Antoine Rolet, Sho SONODA
05:10 PM short Q&A session with plenary speakers
05:30 PM Closing session