Marco Cuturi

Schedule 09:00am - 10:00am: Marco Cuturi 10:00am - 10:30am: coffee break 10:30am - 11:00am: Andrew Warren 11:00am - 11:30am: Rentian Yao 11:30am - 12:00pm: Jakwang Kim 12:00pm - 01:00pm: Lunch (sandwich) 01:00pm - 01:30pm: Sybille Marcotte 01:30pm -...

I will introduce our recent work on parameterising OT problems with elastic costs, i.e. ground costs that mix the classic squared Euclidean distance with a regularizer (e.g. L1 norm). After highlighting the properties of OT maps that follow such...

A recent wave of contributions in machine learning center on the concept of generative models for extremely complex data such as natural images. These approaches provide principled ways to use deep network architectures, large datasets and automatic...

Optimal transport theory provides practitioners from statistics, imaging, graphics or machine learning with a very powerful toolbox to compare probability measures. These tools translate however in their original form into computational schemes that...