Stochastic adaptive regularization with dynamic sampling for machine learning

, et

référence BibTeX

In this paper, we consider both first- and second-order techniques to address continuous optimization problems arising in machine learning. In the first-order case, we propose a framework of transition from deterministic or semi-deterministic to stochastic quadratic regularization methods. We leverage the two-phase nature of stochastic optimization to propose a novel first-order algorithm with adaptive sampling and adaptive step size. In the second-order case, we propose a novel stochastic damped L-BFGS method that improves on previous algorithms in the highly nonconvex context of deep learning. Both algorithms are evaluated on well-known deep learning datasets and exhibit promising performance.

, 17 pages

Ce cahier a été révisé en juin 2021

Axe de recherche

Application de recherche


G2051R.pdf (700 Ko)