Optimal Transport meets Probability, Statistics and Machine Learning (17w5093)

Organizers

(Université Paris Dauphine)

(ENSAE)

Brendan Pass (University of Alberta)

Carola Schönlieb (University of Cambridge)

Description

The Casa Matemática Oaxaca (CMO) will host the "Optimal Transport meets Probability, Statistics and Machine Learning" workshop from April 30th to May 5th, 2017.



What is the most efficient way to transport coal from mines to factories? How can one put color in the style of Andy Warhol on a black and white portrait of Humphrey Bogart? These are seemingly unrelated questions. However, they can be addressed by the same mathematical theory: Optimal Transport. Optimal transport can be traced to the work of Monge before the French Revolution, and has been an extremely successful theory with applications in many different areas of Mathematics in the last 25 years. Cédric Villani, who was awaded the Fields medal in 2010, wrote a thousand pages book on the topic!

This workshop aims at understanding how optimal transport can be used to efficiently extract relevant information from huge and complex datasets (such as vast collections of HD images, politician speeches, postings on social networks...).



The Casa Matemática Oaxaca (CMO) in Mexico, and the Banff International Research Station for Mathematical Innovation and Discovery (BIRS) in Banff, are collaborative Canada-US-Mexico ventures that provide an environment for creative interaction as well as the exchange of ideas, knowledge, and methods within the Mathematical Sciences, with related disciplines and with industry.

The research station in Banff is supported by Canada's Natural Science and Engineering Research Council (NSERC), the U.S. National Science Foundation (NSF), Alberta's Advanced Education and Technology, and Mexico's Consejo Nacional de Ciencia y Tecnología (CONACYT). The research station in Oaxaca is funded by CONACYT.