English

Accelerated Gradient Descent for Faster Convergence with Minimal Overhead

Machine Learning 2026-05-18 v1

Abstract

In this paper, we present CT-AGD (Curvature-Tuned Accelerated Gradient Descent), an optimization method for non-convex optimization problems in deep learning training tasks. CT-AGD is a general boosting procedure that accelerates first-order methods by explicitly capturing the local curvature using finite-difference quotients, and the development of heuristics aimed at mitigating noise and bias introduced by stochastic mini-batch training. CT-AGD has a comparable storage and computational overhead as adaptive gradient methods such as Adam. Our extensive experiments demonstrate that CT-AGD achieves the same level of accuracy as the baseline first-order methods, yet reduces the required training epochs by 33% on average.

Keywords

Cite

@article{arxiv.2605.16017,
  title  = {Accelerated Gradient Descent for Faster Convergence with Minimal Overhead},
  author = {Manuel Graca and L. Miguel Silveira and Arlindo Oliveira and Frank Liu},
  journal= {arXiv preprint arXiv:2605.16017},
  year   = {2026}
}

Comments

17 pages

R2 v1 2026-07-22T07:14:36.915Z