English

Adaptive control mechanisms in gradient descent algorithms

Optimization and Control 2025-08-27 v1 Systems and Control Systems and Control

Abstract

The problem of designing adaptive stepsize sequences for the gradient descent method applied to convex and locally smooth functions is studied. We take an adaptive control perspective and design update rules for the stepsize that make use of both past (measured) and future (predicted) information. We show that Lyapunov analysis can guide in the systematic design of adaptive parameters striking a balance between convergence rates and robustness to computational errors or inexact gradient information. Theoretical and numerical results indicate that closed-loop adaptation guided by system theory is a promising approach for designing new classes of adaptive optimization algorithms with improved convergence properties.

Keywords

Cite

@article{arxiv.2508.19100,
  title  = {Adaptive control mechanisms in gradient descent algorithms},
  author = {Andrea Iannelli},
  journal= {arXiv preprint arXiv:2508.19100},
  year   = {2025}
}

Comments

Accepted to the IEEE Conference on Decision and Control 2025

R2 v1 2026-07-01T05:06:56.552Z