paper-with-me

홈 › Papers

Linearly convergent stochastic heavy ball method for minimizing generalization error

2017-10-30 · Nicolas Loizou, Peter Richtárik

In this work we establish the first linear convergence result for the stochastic heavy ball method. The method performs SGD steps with a fixed stepsize, amended by a heavy ball momentum term. In the analysis, we focus on minimizing the expected loss and not on finite-sum minimization, which is typically a much harder problem. While in the analysis we constrain ourselves to quadratic loss, the overall objective is not necessarily strongly convex.

📄 PDF Abstract BibTeX arXiv:1710.10737

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models

2021-06-07 · NeurIPS 2021 12 · Courtney Paquette, Elliot Paquette

We analyze a class of stochastic gradient algorithms with momentum on a high-dimensional random least squares problem. Our framework, inspired by random matrix theory, provides an exact (deterministic) characterization f…

Gradient Temporal Difference with Momentum: Stability and Convergence

2021-11-22 · Rohan Deb, Shalabh Bhatnagar

Gradient temporal difference (Gradient TD) algorithms are a popular class of stochastic approximation (SA) algorithms used for policy evaluation in reinforcement learning. Here, we consider Gradient TD algorithms with an…

$N$-Timescale Stochastic Approximation: Stability and Convergence

2021-12-07 · Rohan Deb, Shalabh Bhatnagar

This paper presents the first sufficient conditions that guarantee the stability and almost sure convergence of $N$-timescale stochastic approximation (SA) iterates for any $N\geq1$. It extends the existing results on On…

Approximate and Stochastic Greedy Optimization

2017-05-25 · Ye Nan, Bartlett Peter

We consider two greedy algorithms for minimizing a convex function in a bounded convex set: an algorithm by Jones [1992] and the Frank-Wolfe (FW) algorithm. We first consider approximate versions of these algorithms. For…

A New Variant of Stochastic Heavy ball Optimization Method for Deep Learning

2021-01-01 · Zhou Shao, Tong Lin

Stochastic momentum optimization methods, also known as stochastic heavy ball (SHB) methods, are one of the most popular optimization methods for deep learning. These methods can help accelerate stochastic gradient desce…

Deep Learning