paper-with-me

홈 › Papers

signProx: One-Bit Proximal Algorithm for Nonconvex Stochastic Optimization

2018-07-20 · Xiaojian Xu, Ulugbek S. Kamilov

Stochastic gradient descent (SGD) is one of the most widely used optimization methods for parallel and distributed processing of large datasets. One of the key limitations of distributed SGD is the need to regularly communicate the gradients between different computation nodes. To reduce this communication bottleneck, recent work has considered a one-bit variant of SGD, where only the sign of each gradient element is used in optimization. In this paper, we extend this idea by proposing a stochastic variant of the proximal-gradient method that also uses one-bit per update element. We prove the theoretical convergence of the method for non-convex optimization under a set of explicit assumptions. Our results indicate that the compressed method can match the convergence rate of the uncompressed one, making the proposed method potentially appealing for distributed processing of large datasets.

📄 PDF Abstract BibTeX arXiv:1807.08023

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

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

Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization

2016-12-01 · NeurIPS 2016 12 · Sashank J. Reddi, Suvrit Sra, Barnabas Poczos, Alexander J. Smola

We analyze stochastic algorithms for optimizing nonconvex, nonsmooth finite-sum problems, where the nonsmooth part is convex. Surprisingly, unlike the smooth case, our knowledge of this fundamental problem is very limit…

Fast Stochastic Methods for Nonsmooth Nonconvex Optimization

2016-05-23 · Sashank J. Reddi, Suvrit Sra, Barnabas Poczos, Alex Smola

We analyze stochastic algorithms for optimizing nonconvex, nonsmooth finite-sum problems, where the nonconvex part is smooth and the nonsmooth part is convex. Surprisingly, unlike the smooth case, our knowledge of this f…

Asynchronous Stochastic Proximal Methods for Nonconvex Nonsmooth Optimization

2018-02-24 · Rui Zhu, Di Niu, Zongpeng Li

We study stochastic algorithms for solving nonconvex optimization problems with a convex yet possibly nonsmooth regularizer, which find wide applications in many practical machine learning applications. However, compared…

Stochastic Variance Reduction Gradient for a Non-convex Problem Using Graduated Optimization

2017-07-10 · Li Chen, Shuisheng Zhou, Zhuan Zhang

In machine learning, nonconvex optimization problems with multiple local optimums are often encountered. Graduated Optimization Algorithm (GOA) is a popular heuristic method to obtain global optimums of nonconvex problem…

Faster Gradient-Free Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization

2019-02-16 · Feihu Huang, Bin Gu, Zhouyuan Huo, Songcan Chen 외

Proximal gradient method has been playing an important role to solve many machine learning tasks, especially for the nonsmooth problems. However, in some machine learning problems such as the bandit model and the black-b…

BIG-bench Machine Learning