paper-with-me

홈 › Papers

A Stochastic Gradient Method with an Exponential Convergence _Rate for Finite Training Sets

2012-12-01 · NeurIPS 2012 12 · Nicolas L. Roux, Mark Schmidt, Francis R. Bach

We propose a new stochastic gradient method for optimizing the sum of
 a finite set of smooth functions, where the sum is strongly convex.
 While standard stochastic gradient methods
 converge at sublinear rates for this problem, the proposed method incorporates a memory of previous gradient values in order to achieve a linear convergence 
rate. In a machine learning context, numerical experiments indicate that the new algorithm can dramatically outperform standard
 algorithms, both in terms of optimizing the training error and reducing the test error quickly.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Exponential convergence of testing error for stochastic gradient methods

2017-12-13 · Loucas Pillaud-Vivien, Alessandro Rudi, Francis Bach

We consider binary classification problems with positive definite kernels and square loss, and study the convergence rates of stochastic gradient methods. We show that while the excess testing loss (squared loss) converg…

Binary ClassificationClassificationGeneral Classification

Convergence of Stochastic Gradient Langevin Dynamics in the Lazy Training Regime

2025-10-24 · Noah Oberweis, Semih Cayci arxiv

Continuous-time models provide important insights into the training dynamics of optimization algorithms in deep learning. In this work, we establish a non-asymptotic convergence analysis of stochastic gradient Langevin d…

Path convergence of Markov chains on large graphs

2023-08-18 · Siva Athreya, Soumik Pal, Raghav Somani, Raghavendra Tripathi

We consider two classes of natural stochastic processes on finite unlabeled graphs. These are Euclidean stochastic optimization algorithms on the adjacency matrix of weighted graphs and a modified version of the Metropol…

Stochastic Optimization

Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization

2021-09-29 · ICLR 2022 4 · Kazusato Oko, Taiji Suzuki, Atsushi Nitanda, Denny Wu

We introduce Particle-SDCA, a gradient-based optimization algorithm for two-layer neural networks in the mean field regime that achieves exponential convergence rate in regularized empirical risk minimization. The propos…

Dimension-free convergence rates for gradient Langevin dynamics in RKHS

2020-02-29 · Boris Muzellec, Kanji Sato, Mathurin Massias, Taiji Suzuki

Gradient Langevin dynamics (GLD) and stochastic GLD (SGLD) have attracted considerable attention lately, as a way to provide convergence guarantees in a non-convex setting. However, the known rates grow exponentially wit…