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

📅 2024-08-06
🏛️ arXiv.org
📈 Citations: 1
Influential: 0
📄 PDF

career value

204K/year
🤖 AI Summary
This work addresses the convergence guarantees of stochastic line search optimization for over-parameterized models under interpolation conditions. We establish a necessary and sufficient condition on the search direction—applicable to a broad class of methods—that ensures finite termination and bounded backtracking steps, and rigorously prove linear convergence under the Polyak–Łojasiewicz (PL) assumption. The condition unifies major first-order strategies—including momentum, conjugate gradient, and adaptive preconditioning—providing a verifiable theoretical foundation for their principled integration with stochastic line search. Our analysis fills a critical gap in the convergence theory of stochastic line search methods and significantly extends both the applicability and reliability of efficient first-order optimization in interpolation learning regimes.

Technology Category

Application Category

📝 Abstract
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 on approaches based on stochastic line searches and employing general search directions. We define conditions on the sequence of search directions that guarantee finite termination and bounds for the backtracking procedure. Moreover, we shed light on the additional property of directions needed to prove fast (linear) convergence of the general class of algorithms when applied to PL functions in the interpolation regime. From the point of view of algorithms design, the proposed analysis identifies safeguarding conditions that could be employed in relevant algorithmic framework. In particular, it could be of interest to integrate stochastic line searches within momentum, conjugate gradient or adaptive preconditioning methods.
Problem

Research questions and friction points this paper is trying to address.

Analyzing convergence of stochastic line search for over-parametrized models
Defining conditions for finite termination in backtracking procedures
Identifying fast convergence properties for PL functions in interpolation
Innovation

Methods, ideas, or system contributions that make the work stand out.

Stochastic line search for over-parametrized models
General search directions with finite termination
Fast convergence for PL functions
M
Matteo Lapucci
Department of Information Engineering, University of Florence, V ia di Santa Marta 3, Firenze, 50139, Italy
D
Davide Pucci
Department of Information Engineering, University of Florence, V ia di Santa Marta 3, Firenze, 50139, Italy