paper-with-me

Papers

A Stochastic Newton Algorithm for Distributed Convex Optimization

2021-10-07 · NeurIPS 2021 12 · Brian Bullins, Kumar Kshitij Patel, Ohad Shamir, Nathan Srebro, Blake Woodworth

We propose and analyze a stochastic Newton algorithm for homogeneous distributed stochastic convex optimization, where each machine can calculate stochastic gradients of the same population objective, as well as stochastic Hessian-vector products (products of an independent unbiased estimator of the Hessian of the population objective with arbitrary vectors), with many such stochastic computations performed between rounds of communication. We show that our method can reduce the number, and frequency, of required communication rounds compared to existing methods without hurting performance, by proving convergence guarantees for quasi-self-concordant objectives (e.g., logistic regression), alongside empirical evidence.

📄 PDF Abstract BibTeX arXiv:2110.02954

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization

2018-06-07 · ICML 2018 · Umut Şimşekli, Çağatay Yıldız, Thanh Huy Nguyen, Gaël Richard 외

Recent studies have illustrated that stochastic gradient Markov Chain Monte Carlo techniques have a strong potential in non-convex optimization, where local and global convergence guarantees can be shown under certain co…

Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization

2018-07-01 · ICML 2018 7 · Umut Simsekli, Cagatay Yildiz, Than Huy Nguyen, Taylan Cemgil 외

Recent studies have illustrated that stochastic gradient Markov Chain Monte Carlo techniques have a strong potential in non-convex optimization, where local and global convergence guarantees can be shown under certa…

A Stochastic Semismooth Newton Method for Nonsmooth Nonconvex Optimization

2018-03-09 · Andre Milzarek, Xiantao Xiao, Shicong Cen, Zaiwen Wen 외

In this work, we present a globalized stochastic semismooth Newton method for solving stochastic optimization problems involving smooth nonconvex and nonsmooth convex terms in the objective function. We assume that only …

Binary ClassificationStochastic Optimization

Communication-Efficient Distributed Optimization of Self-Concordant Empirical Loss

2015-01-01 · Yuchen Zhang, Lin Xiao

We consider distributed convex optimization problems originated from sample average approximation of stochastic optimization, or empirical risk minimization in machine learning. We assume that each machine in the distrib…

Binary ClassificationDistributed ComputingDistributed Optimizationregression+1

Nys-Newton: Nyström-Approximated Curvature for Stochastic Optimization

2021-10-16 · Dinesh Singh, Hardik Tankaria, Makoto Yamada

Second-order optimization methods are among the most widely used optimization approaches for convex optimization problems, and have recently been used to optimize non-convex optimization problems such as deep learning mo…

Stochastic Optimization