paper-with-me

홈 › Papers

A Stochastic Variance Reduced Gradient using Barzilai-Borwein Techniques as Second Order Information

2022-08-23 · Hardik Tankaria, Nobuo Yamashita

In this paper, we consider to improve the stochastic variance reduce gradient (SVRG) method via incorporating the curvature information of the objective function. We propose to reduce the variance of stochastic gradients using the computationally efficient Barzilai-Borwein (BB) method by incorporating it into the SVRG. We also incorporate a BB-step size as its variant. We prove its linear convergence theorem that works not only for the proposed method but also for the other existing variants of SVRG with second-order information. We conduct the numerical experiments on the benchmark datasets and show that the proposed method with constant step size performs better than the existing variance reduced methods for some test problems.

📄 PDF Abstract BibTeX arXiv:2208.11075

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

A variable metric mini-batch proximal stochastic recursive gradient algorithm with diagonal Barzilai-Borwein stepsize

2020-10-02 · Tengteng Yu, Xin-Wei Liu, Yu-Hong Dai, Jie Sun

Variable metric proximal gradient methods with different metric selections have been widely used in composite optimization. Combining the Barzilai-Borwein (BB) method with a diagonal selection strategy for the metric, th…

Barzilai-Borwein Step Size for Stochastic Gradient Descent

2016-05-13 · NeurIPS 2016 12 · Conghui Tan, Shiqian Ma, Yu-Hong Dai, Yuqiu Qian

One of the major issues in stochastic gradient descent (SGD) methods is how to choose an appropriate step size while running the algorithm. Since the traditional line search technique does not apply for stochastic optimi…

Stochastic Optimization

Stochastic Non-convex Ordinal Embedding with Stabilized Barzilai-Borwein Step Size

2017-11-17 · Ke Ma, Jinshan Zeng, Jiechao Xiong, Qianqian Xu 외

Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years. Most of the existing methods are batch methods designed mainly based on the convex opt…

An Adaptive Incremental Gradient Method With Support for Non-Euclidean Norms

2022-04-28 · Binghui Xie, Chenhan Jin, Kaiwen Zhou, James Cheng 외

Stochastic variance reduced methods have shown strong performance in solving finite-sum problems. However, these methods usually require the users to manually tune the step-size, which is time-consuming or even infeasibl…

Accelerating Mini-batch SARAH by Step Size Rules

2019-06-20 · Zhuang Yang, Zengping Chen, Cheng Wang

StochAstic Recursive grAdient algoritHm (SARAH), originally proposed for convex optimization and also proven to be effective for general nonconvex optimization, has received great attention due to its simple recursive fr…