An Adaptive Gradient Method with Energy and Momentum
This work addresses optimization challenges in large-scale machine learning, offering an incremental improvement over existing methods like SGD with momentum and Adam.
The paper tackles the problem of gradient-based optimization for stochastic objective functions by introducing a novel algorithm that adapts learning rates using an 'energy' variable, resulting in fast convergence and competitive generalization compared to SGD with momentum and Adam in deep neural network training.
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.