|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Regularized Optimal Transport and Applications
If you have a question about this talk, please contact lecturescam.
Please be aware that this event may be recorded. Microsoft will own the copyright of any recording and reserves the right to distribute it as required.
Optimal transport theory provides tools to compare probability measures. After reviewing the basics of optimal transport distances (a.k.a Wasserstein or Earth Mover’s), I will show how an adequate regularization of the optimal problem can result in substantially faster computations and much better behaved numerical computations. I will then show how this regularization can enable several applications of optimal transport to learn from probability measures, from the computation of barycenters to that of dictionaries or PCA , all carried out using the Wasserstein geometry.
This talk is part of the Microsoft Research Cambridge, public talks series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsEMBL-EBI Science and Society Programme Cambridge Network Healthcare SIG Economic and Social History Graduate Workshop
Other talksResearch Conference and Showcase - Research and Practice: Making the connections EU Life Lecture - “Rembrandt: Remodelling the brain in intellectual disability” Traces in non-semisimple categories A pious home? Italian Renaissance devotional jewellery and amulets The Art & Science of Clinical Problem-Solving Exotic lattices and simple locally compact groups