Without-Replacement Sampling for Stochastic Gradient Methods:
Convergence Results and Application to Distributed Optimization

v1v2v3 (latest)

Without-Replacement Sampling for Stochastic Gradient Methods: Convergence Results and Application to Distributed Optimization

2 March 2016

ArXiv (abs)PDF HTML

Papers citing "Without-Replacement Sampling for Stochastic Gradient Methods: Convergence Results and Application to Distributed Optimization"

10 / 10 papers shown

Title
Introduction to Online Convex Optimization Elad Hazan OffRL 175 1,932 0 07 Sep 2019
An Introduction to Matrix Concentration Inequalities J. Tropp 168 1,154 0 07 Jan 2015
Communication-Efficient Distributed Dual Coordinate Ascent Martin Jaggi Virginia Smith Martin Takáč Jonathan Terhorst S. Krishnan Thomas Hofmann Michael I. Jordan 91 353 0 04 Sep 2014
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives Aaron Defazio Francis R. Bach Simon Lacoste-Julien ODL 133 1,826 0 01 Jul 2014
A simpler approach to obtaining an O(1/t) convergence rate for the projected stochastic subgradient method Simon Lacoste-Julien Mark Schmidt Francis R. Bach 183 260 0 10 Dec 2012
Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes Ohad Shamir Tong Zhang 151 574 0 08 Dec 2012
Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization Shai Shalev-Shwartz Tong Zhang 184 1,033 0 10 Sep 2012
Beneath the valley of the noncommutative arithmetic-geometric mean inequality: conjectures, case-studies, and consequences Benjamin Recht Christopher Ré 64 51 0 19 Feb 2012
A Reliable Effective Terascale Linear Learning System Alekh Agarwal O. Chapelle Miroslav Dudík John Langford 94 418 0 19 Oct 2011
Better Mini-Batch Algorithms via Accelerated Gradient Methods Andrew Cotter Ohad Shamir Nathan Srebro Karthik Sridharan ODL 120 314 0 22 Jun 2011

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.