Sinkhorn Divergences: Bridging the gap between Optimal Transport and MMD
Dec 13, 2019
Speakers
Aude Genevay
Speaker · 0 followers
About
Sinkhorn Divergences, based on entropy-regularized OT, were first introduced by Cuturi in 2013 as a solution to the computational burden of OT. However, this family of losses actually interpolates between OT (no regularization) and MMD (infinite regularization). This interpolation property is also true in terms of sample complexity, and thus regularizing OT breaks its curse of dimension. We will illustrate these theoretical claims on a set of learning problems like learning a distribution from samples.Sinkhorn Divergences, based on entropy-regularized OT, were first introduced by Cuturi in 2013 as a solution to the computational burden of OT. However, this family of losses actually interpolates between OT (no regularization) and MMD (infinite regularization). This interpolation property is also true in terms of sample complexity, and thus regularizing OT breaks its curse of dimension. We will illustrate these theoretical claims on a set of learning problems like learning a distribution from s…
Categories
Mathematics
Category · 2.4k presentations
AI & Data Science
Category · 10.8k presentations
About NIPS 2019
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
First Steps Towards Collaborative Poetry Generation
Watch later
Efficiently Breaking the Curse of Horizon with Double Reinforcement Learning
Watch later
Representation Learning and Fairness
Watch later
Track 4 Session 2 Spotlights 2
Watch later
Adil Salim, …
