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

07/05/2021
by   Waïss Azizian, et al.
0

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.).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/15/2022

On the rate of convergence of Bregman proximal methods in constrained variational inequalities

We examine the last-iterate convergence rate of Bregman proximal methods...
research
10/31/2022

Almost Sure Convergence Rates of Stochastic Zeroth-order Gradient Descent for Łojasiewicz Functions

We prove almost sure convergence rates of Zeroth-order Gradient Descent ...
research
11/15/2020

Simple and optimal methods for stochastic variational inequalities, II: Markovian noise and policy evaluation in reinforcement learning

The focus of this paper is on stochastic variational inequalities (VI) u...
research
02/02/2022

Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions

Performance of optimization on quadratic problems sensitively depends on...
research
01/28/2023

Unbiased estimators for the Heston model with stochastic interest rates

We combine the unbiased estimators in Rhee and Glynn (Operations Researc...
research
02/10/2019

Deducing Kurdyka-Łojasiewicz exponent via inf-projection

Kurdyka-Łojasiewicz (KL) exponent plays an important role in estimating ...
research
06/09/2021

Mixture weights optimisation for Alpha-Divergence Variational Inference

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

Please sign up or login with your details

Forgot password? Click here to reset