Accelerated Gradient Descent for Faster Convergence with Minimal Overhead
Provides a practical acceleration technique for deep learning practitioners seeking faster convergence without significant overhead.
CT-AGD accelerates first-order optimization methods for deep learning by capturing local curvature, achieving 33% fewer training epochs while maintaining accuracy.
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.