Non-Convex Stochastic Composite Optimization with Polyak Momentum

arXiv:2403.02967v1 Announce Type: cross
Abstract: The stochastic proximal gradient method is a powerful generalization of the widely used stochastic gradient descent (SGD) method and has found numerous applications in Machine Learning. However, it is notoriously known that this method fails to converge in non-convex settings where the stochastic noise is significant (i.e. when only small or bounded batch sizes are used). In this paper, we focus on the stochastic proximal gradient method with Polyak momentum. We prove this method attains …

abstract applications arxiv converge cs.lg found gradient machine machine learning math.oc noise optimization stochastic type