Speaker |
Marco Cuturi |
|---|---|
Affiliation |
CREST-ENSAE/Université Paris-Saclay |
Date |
Friday, 25 May 2018 |
Time |
13:00-14:00 |
Location |
Zoom |
Link |
Roberts Building G08 Sir David Davies LT |
Event series |
DeepMind/ELLIS CSML Seminar Series |
Abstract |
Machine learning deals with objects that are structured. Two common structures arising in applications are point clouds / histograms, as well as time series. Early progress in optimization (linear and dynamic programming) have provided powerful families of distances between these structures, namely Wasserstein distances and dynamic time warping scores. Because they rely both on the minimization of a linear functional over respectively a polyhedral set of couplings and a (discrete) space of alignments, both result in non-differentiable quantities. We show how two distinct smoothing strategies result in quantities that are better behaved and more suitable for machine learning applications, with applications to several tasks arising in ML (clustering, structured prediction) |
Biography |