Stochastic optimization on matrices and a graphon McKean-Vlasov limit

TL;DR

This paper studies the behavior of stochastic gradient descent on large symmetric matrices and their limits as graphons, extending McKean-Vlasov theory to a new infinite-dimensional, exchangeable array setting.

Contribution

It introduces a novel framework for analyzing stochastic gradient flows on matrices and graphons, including reflected diffusions and a new propagation of chaos concept.

Findings

Deterministic limits of matrix-valued stochastic gradients as dimensions grow large.

Extension of McKean-Vlasov limits to graphon-based stochastic processes.

Characterization of stochastic limits via reflected diffusions and differential equations.

Abstract

We consider stochastic gradient descents on the space of large symmetric matrices of suitable functions that are invariant under permuting the rows and columns using the same permutation. We establish deterministic limits of these random curves as the dimensions of the matrices go to infinity while the entries remain bounded. Under a ``small noise'' assumption the limit is shown to be the gradient flow of functions on graphons whose existence was established in Oh, Somani, Pal, and Tripathi, \texit{J Theor Probab 37, 1469--1522 (2024)}. We also consider limits of stochastic gradient descents with added properly scaled reflected Brownian noise. The limiting curve of graphons is characterized by a family of stochastic differential equations with reflections and can be thought of as an extension of the classical McKean-Vlasov limit for interacting diffusions to the graphon setting. The proofs introduce a family of infinite-dimensional exchangeable arrays of reflected diffusions and a novel notion of propagation of chaos for large matrices of diffusions converging to such arrays in a suitable sense.