Stochastic Dynamics Near Critical Points in Stochastic Gradient Descent

The talk will focus on limit theorems for stochastic gradient descent (SGD) and on how the choice of step size affects its convergence. We will begin by discussing the convergence of deterministic gradient descent with a constant step size, then review the classical Robbins–Monro result for SGD, and finally turn to several results from our joint work [1] concerning the convergence of SGD with a constant step size that tends to zero.

The talk will be streamed through "Kontur Talk": https://imsoran.ktalk.ru/ogsac0ijeetj