Speaker
Ivan Oseledets
(Skolkovo Institute of Science and Technology, Moscow)
Description
In this talk, I will discuss recent advances and challenges in the approximation of high-dimensional probability
distributions, knowing only its samples $x_1, \ldots, x_n$.
Such problems appear in many applications. I will discuss techniques such as normalising flows, diffusion models and flow matching.
Primary author
Ivan Oseledets
(Skolkovo Institute of Science and Technology, Moscow)
