An Adaptive Gradient Method with Energy and Momentum

TL;DR

This paper presents an adaptive gradient optimization algorithm that combines energy and momentum, offering improved convergence and generalization for large-scale machine learning tasks, including deep neural networks.

Contribution

Introduces a new adaptive gradient method with energy-based learning rate adjustment, providing theoretical convergence guarantees and practical advantages over existing optimizers.

Findings

Fast convergence demonstrated in experiments

Better generalization compared to SGD with momentum

Competitive performance with Adam

Abstract

We introduce a novel algorithm for gradient-based optimization of stochastic objective functions. The method may be seen as a variant of SGD with momentum equipped with an adaptive learning rate automatically adjusted by an 'energy' variable. The method is simple to implement, computationally efficient, and well suited for large-scale machine learning problems. The method exhibits unconditional energy stability for any size of the base learning rate. We provide a regret bound on the convergence rate under the online convex optimization framework. We also establish the energy-dependent convergence rate of the algorithm to a stationary point in the stochastic non-convex setting. In addition, a sufficient condition is provided to guarantee a positive lower threshold for the energy variable. Our experiments demonstrate that the algorithm converges fast while generalizing better than or as well as SGD with momentum in training deep neural networks, and compares also favorably to Adam.