Convergence Conditions for Stochastic Line Search Based Optimization of Over-parametrized Models

M Lapucci, D Pucci - arxiv preprint arxiv:2408.03199, 2024 - arxiv.org
In this paper, we deal with algorithms to solve the finite-sum problems related to fitting over-
parametrized models, that typically satisfy the interpolation condition. In particular, we focus …

Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum Problems

M Lapucci, D Pucci - arxiv preprint arxiv:2411.07102, 2024 - arxiv.org
In this work, we address unconstrained finite-sum optimization problems, with particular
focus on instances originating in large scale deep learning scenarios. Our main interest lies …