The Last-Iterate Convergence Rate of Optimistic Mirror Descent in Stochastic Variational Inequalities

by   Waïss Azizian, et al.

In this paper, we analyze the local convergence rate of optimistic mirror descent methods in stochastic variational inequalities, a class of optimization problems with important applications to learning theory and machine learning. Our analysis reveals an intricate relation between the algorithm's rate of convergence and the local geometry induced by the method's underlying Bregman function. We quantify this relation by means of the Legendre exponent, a notion that we introduce to measure the growth rate of the Bregman divergence relative to the ambient norm near a solution. We show that this exponent determines both the optimal step-size policy of the algorithm and the optimal rates attained, explaining in this way the differences observed for some popular Bregman functions (Euclidean projection, negative entropy, fractional power, etc.).


page 1

page 2

page 3

page 4


Convergence Rates for Deterministic and Stochastic Subgradient Methods Without Lipschitz Continuity

We generalize the classic convergence rate theory for subgradient method...

Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions

Performance of optimization on quadratic problems sensitively depends on...

On the convergence of single-call stochastic extra-gradient methods

Variational inequalities have recently attracted considerable interest i...

Deducing Kurdyka-Łojasiewicz exponent via inf-projection

Kurdyka-Łojasiewicz (KL) exponent plays an important role in estimating ...

Mixture weights optimisation for Alpha-Divergence Variational Inference

This paper focuses on α-divergence minimisation methods for Variational ...