Коллоквиум ФКН: Perturbed Proximal Gradient Algorithms. Докладчик: Eric Moulines (École Polytechnique, Франция)
22 февраля, 18:10 – 19:30, ауд. 317
Eric Moulines (École Polytechnique, Франция)Perturbed Proximal Gradient Algorithms
We study a version of the proximal gradient algorithm for which the gradient is intractable and is approximated by Monte Carlo methods (and in particular Markov Chain Monte Carlo). We derive conditions on the step size and the Monte Carlo batch size under which convergence is guaranteed: both increasing batch size and constant batch size are considered. We also derive non-asymptotic bounds for an averaged version. Our results cover both the cases of biased and unbiased Monte Carlo approximation. To support our findings, we discuss the inference of a sparse generalized linear model with random effect and the problem of learning the edge structure and parameters of sparse undirected graphical models.
Приглашаются все желающие.
Место проведения: Кочновский проезд, 3, ауд. 317 (3 этаж)
Для участия в мероприятии и для заказа пропуска в здание необходимо зарегистрироваться.