Mathematics of Machine Learning

April 14 – May 11, 2018

Organizers: Sebastian Bubeck (Microsoft Research), Luc Devroye (McGill), Gábor Lugosi (Pompeu Fabra)

The thematic activity focuses on mathematical challenges of machine learning. The spectacular success of machine learning in a wide range of applications opens many exciting theoretical challenges in a number of mathematical fields, including probability, statistics, combinatorics, optimization, and geometry. The CRM will bring together researchers of machine learning and mathematics to discuss these problems. The principal topics include combinatorial statistics, online learning, and deep neural networks.

The main activities include a workshop on “Combinatorial Statistics” and another one on “Modern Challenges in Learning Theory,” as well as regular seminars given by the invited researchers and scholars-in-residence.

The program will go as follow.

Week 1 (Monday April 16-Friday April 20)
Opening week.
Opening keynote lecture on Monday April 16.
Arrival of the Simons Foundations researchers in residence.

Week 2 (Monday April 23-Friday April 27)
“Workshop on Learning Theory”.
24 invited speakers.
Open to all scholars.
Small registration will apply to all attendees.

Week 3 (Monday April 30-Friday May 4)
“Workshop on Combinatorial Statistics” (by invitation only).
One minicourse (TBA)

Week 4 (Monday May 7-Friday May 11)
Closing keynote lecture on Friday May 11.