14-21 July 2024

The school is going to introduce the participants to problems and techniques that lie at the rich interface of high-dimensional probability, convex geometry, machine learning and optimal transport. Theoretical foundations of machine learning are based on high-dimensional probability, an area guided by geometric insight.

Four leading researchers who work in those areas will give courses of lectures in the school. Augusto Gerolin (University of Ottawa, Canada, LMS Distinguished Visiting Fellow at ICMU) built bridges between machine learning and optimal transport. Mark Rudelson (University of Michigan, USA) established seminal results connecting high-dimensional probability and high-dimensional convex geometry. Károly Böröczky (Alfréd Rényi Institute of Mathematics, Hungary) is advancing Euclidean geometry in a broad sense, and in particular high-dimensional convex geometry. Piotr Nayar (University of Warsaw, Poland) works on the interface of probability, convex geometry, with connections to information theory.

Apply for participation

Please apply before April 30


Galyna Livshyts, Georgia Tech

Andriy Prymak, University of Manitoba

Kateryna Tatarko, University of Waterloo

Roman Vershynin, University of California, Irvine

Vlad Yaskin, University of Alberta

Tetyana Zakharchenko, Ukrainian Catholic University