paper-with-me

Papers

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

2024-08-06 · Matteo Lapucci, Davide Pucci

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 frameworks. In particular, it could be of interest to integrate stochastic line searches within momentum, conjugate gradient or adaptive preconditioning methods.

📄 PDF Abstract BibTeX arXiv:2408.03199

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Accelerated Stochastic Quasi-Newton Optimization on Riemann Manifolds

2017-04-06 · Anirban Roychowdhury

We propose an L-BFGS optimization algorithm on Riemannian manifolds using minibatched stochastic variance reduction techniques for fast convergence with constant step sizes, without resorting to linesearch methods design…

Linear Convergence of Generalized Mirror Descent with Time-Dependent Mirrors

2020-09-18 · Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

The Polyak-Lojasiewicz (PL) inequality is a sufficient condition for establishing linear convergence of gradient descent, even in non-convex settings. While several recent works use a PL-based analysis to establish linea…

A preconditioned accelerated stochastic gradient descent algorithm

2019-05-01 · ICLR 2019 5 · Alexandru Onose, Seyed Iman Mossavat, Henk-Jan H. Smilde

We propose a preconditioned accelerated stochastic gradient method suitable for large scale optimization. We derive sufficient convergence conditions for the minimization of convex functions using a generic class of diag…

Stochastic Optimization

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates

2019-05-24 · NeurIPS 2019 12 · Sharan Vaswani, Aaron Mishkin, Issam Laradji, Mark Schmidt 외

Recent works have shown that stochastic gradient descent (SGD) achieves the fast convergence rates of full-batch gradient descent for over-parameterized models satisfying certain interpolation conditions. However, the st…

General ClassificationMulti-class Classification

A Unified Convergence Theorem for Stochastic Optimization Methods

2022-06-08 · Xiao Li, Andre Milzarek

In this work, we provide a fundamental unified convergence theorem used for deriving expected and almost sure convergence results for a series of stochastic optimization methods. Our unified theorem only requires to veri…

Stochastic Optimization