AI RESEARCH
Accelerated Gradient Descent for Faster Convergence with Minimal Overhead
arXiv CS.LG
•
ArXi:2605.16017v1 Announce Type: new In this paper, we present CT-AGD (Curvature-Tuned Accelerated Gradient Descent), an optimization method for non-convex optimization problems in 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