On the Role of Data Homogeneity in Multi-Agent Non-convex Stochastic Optimization

TL;DR

This paper investigates how data homogeneity among agents affects the convergence speed of decentralized stochastic gradient descent in non-convex optimization, showing that identical Hessians lead to faster convergence.

Contribution

It provides a new convergence bound for DSGD under Hessian homogeneity, improving previous bounds and highlighting the importance of data similarity.

Findings

Hessian homogeneity reduces the transient time of DSGD.

The transient time bound improves from O(n^2 / ρ^4) to O(n^{4/3} / ρ^{8/3}) with data homogeneity.

Numerical experiments confirm the theoretical advantage of data homogeneity.

Abstract

This paper studies the role of data homogeneity on multi-agent optimization. Concentrating on the decentralized stochastic gradient (DSGD) algorithm, we characterize the transient time, defined as the minimum number of iterations required such that DSGD can achieve comparable performance as its centralized counterpart. When the Hessians for the objective functions are identical at different agents, we show that the transient time of DSGD is $O( n^{4/3} / \rho^{8/3})$ for smooth (possibly non-convex) objective functions, where $n$ is the number of agents and $\rho$ is the spectral gap of connectivity graph. This is improved over the bound of $O( n^2 / \rho^4 )$ without the Hessian homogeneity assumption. Our analysis leverages a property that the objective function is twice continuously differentiable. Numerical experiments are presented to illustrate the essence of data homogeneity to fast convergence of DSGD.