paper-with-me

Papers

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 verify several representative conditions and is not tailored to any specific algorithm. As a direct application, we recover expected and almost sure convergence results of the stochastic gradient method (SGD) and random reshuffling (RR) under more general settings. Moreover, we establish new expected and almost sure convergence results for the stochastic proximal gradient method (prox-SGD) and stochastic model-based methods (SMM) for nonsmooth nonconvex optimization problems. These applications reveal that our unified theorem provides a plugin-type convergence analysis and strong convergence guarantees for a wide class of stochastic optimization methods.

📄 PDF Abstract BibTeX arXiv:2206.03907

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

A Novel Unified Parametric Assumption for Nonconvex Optimization

2025-02-17 · Artem Riabinin, Ahmed Khaled, Peter Richtárik

Nonconvex optimization is central to modern machine learning, but the general framework of nonconvex optimization yields weak convergence guarantees that are too pessimistic compared to practice. On the other hand, while…

Stochastic Optimization

Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization

2020-06-20 · Ahmed Khaled, Othmane Sebbouh, Nicolas Loizou, Robert M. Gower 외

We present a unified theorem for the convergence analysis of stochastic gradient algorithms for minimizing a smooth and convex loss plus a convex regularizer. We do this by extending the unified analysis of Gorbunov, Han…

Quantization

A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent

2019-05-27 · Eduard Gorbunov, Filip Hanzely, Peter Richtárik

In this paper we introduce a unified analysis of a large family of variants of proximal stochastic gradient descent ({\tt SGD}) which so far have required different intuitions, convergence analyses, have different applic…

Quantization

A quantitative Robbins-Siegmund theorem

2024-10-21 · Morenikeji Neri, Thomas Powell

The Robbins-Siegmund theorem is one of the most important results in stochastic optimization, where it is widely used to prove the convergence of stochastic algorithms. We provide a quantitative version of the theorem, e…

Stochastic Optimization

Data augmentation as stochastic optimization

2020-09-28 · Boris Hanin, Yi Sun

We present a theoretical framework recasting data augmentation as stochastic optimization for a sequence of time-varying proxy losses. This provides a unified language for understanding techniques commonly thought of as …

Data AugmentationregressionSchedulingStochastic Optimization