Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:VXTXKXVXrecord.jsonopen to challenge →
read the original abstract
We study the trade-offs between convergence rate and robustness to gradient errors in designing a first-order algorithm. We focus on gradient descent (GD) and accelerated gradient (AG) methods for minimizing strongly convex functions when the gradient has random errors in the form of additive white noise. With gradient errors, the function values of the iterates need not converge to the optimal value; hence, we define the robustness of an algorithm to noise as the asymptotic expected suboptimality of the iterate sequence to input noise power. For this robustness measure, we provide exact expressions for the quadratic case using tools from robust control theory and tight upper bounds for the smooth strongly convex case using Lyapunov functions certified through matrix inequalities. We use these characterizations within an optimization problem which selects parameters of each algorithm to achieve a particular trade-off between rate and robustness. Our results show that AG can achieve acceleration while being more robust to random gradient errors. This behavior is quite different than previously reported in the deterministic gradient noise setting. We also establish some connections between the robustness of an algorithm and how quickly it can converge back to the optimal solution if it is perturbed from the optimal point with deterministic noise. Our framework also leads to practical algorithms that can perform better than other state-of-the-art methods in the presence of random gradient noise.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Distributed Inexact Successive Convex Approximation ADMM: Analysis-Part I
The paper develops two variants of a distributed inexact SCA-ADMM algorithm and proves first-order convergence rate guarantees under mild assumptions for non-convex problems with robustness to errors and delays.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.