English
Related papers

Related papers: An Analysis of Asynchronous Stochastic Accelerated…

200 papers

We show how one can obtain nonaccelerated randomized coordinate descent method (Yu. Nesterov, 2010) and nonaccelerated method of randomization of sum-type functional (Le Roux-Schmidt-Bach, 2012) from the optimal method for the stochastic…

Optimization and Control · Mathematics 2018-05-29 Alexander Gasnikov , Pavel Dvurechensky , Ilnura Usmanova

Parallel computing is a standard approach to achieving high-performance computing (HPC). Three commonly used methods to implement parallel computing include: 1) applying multithreading technology on single-core or multi-core CPUs; 2)…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-18 Xinyao Yi

This paper considers convex programs with a general (possibly non-differentiable) convex objective function and Lipschitz continuous convex inequality constraint functions. A simple algorithm is developed and achieves an $O(1/t)$…

Optimization and Control · Mathematics 2017-08-01 Hao Yu , Michael J. Neely

We consider convex stochastic optimization problems under different assumptions on the properties of available stochastic subgradient. It is known that, if the value of the objective function is available, one can obtain, in parallel,…

Optimization and Control · Mathematics 2017-01-19 Pavel Dvurechensky , Alexander Gasnikov , Anastasia Lagunovskaya

We present a generic framework for parallel coordinate descent (CD) algorithms that includes, as special cases, the original sequential algorithms Cyclic CD and Stochastic CD, as well as the recent parallel Shotgun algorithm. We introduce…

Machine Learning · Computer Science 2012-07-04 Chad Scherrer , Mahantesh Halappanavar , Ambuj Tewari , David Haglin

Training a neural network (NN) typically relies on some type of curve-following method, such as gradient descent (GD) (and stochastic gradient descent (SGD)), ADADELTA, ADAM or limited memory algorithms. Convergence for these algorithms…

Machine Learning · Computer Science 2023-05-08 Michael A Kouritzin , Stephen Styles , Beatrice-Helen Vritsiou

We introduce a proximal version of dual coordinate ascent method. We demonstrate how the derived algorithmic framework can be used for numerous regularized loss minimization problems, including $\ell_1$ regularization and structured output…

Machine Learning · Statistics 2012-11-13 Shai Shalev-Shwartz , Tong Zhang

In this paper we analyze several new methods for solving nonconvex optimization problems with the objective function formed as a sum of two terms: one is nonconvex and smooth, and another is convex but simple and its structure is known.…

Optimization and Control · Mathematics 2014-06-25 A. Patrascu , I. Necoara

Decoupled learning is a branch of model parallelism which parallelizes the training of a network by splitting it depth-wise into multiple modules. Techniques from decoupled learning usually lead to stale gradient effect because of their…

Machine Learning · Computer Science 2020-12-08 Huiping Zhuang , Zhiping Lin , Kar-Ann Toh

Following a series of high-profile drug safety disasters in recent years, many countries are redoubling their efforts to ensure the safety of licensed medical products. Large-scale observational databases such as claims databases or…

Computation · Statistics 2012-08-07 Marc A. Suchard , Shawn E. Simpson , Ivan Zorych , Patrick Ryan , David Madigan

Existing asynchronous distributed optimization algorithms often use diminishing step-sizes that cause slow practical convergence, or fixed step-sizes that depend on an assumed upper bound of delays. Not only is such a delay bound hard to…

Optimization and Control · Mathematics 2023-08-24 Xuyang Wu , Changxin Liu , Sindri Magnusson , Mikael Johansson

In this paper, we propose the Asynchronous Accelerated Nonuniform Randomized Block Coordinate Descent algorithm (A2BCD), the first asynchronous Nesterov-accelerated algorithm that achieves optimal complexity. This parallel algorithm solves…

Optimization and Control · Mathematics 2018-05-22 Robert Hannah , Fei Feng , Wotao Yin

We propose a parallel adaptive constraint-tightening approach to solve a linear model predictive control problem for discrete-time systems, based on inexact numerical optimization algorithms and operator splitting methods. The underlying…

Optimization and Control · Mathematics 2015-03-24 Laura Ferranti , Tamas Keviczky

Over the last decades, Stochastic Gradient Descent (SGD) has been intensively studied by the Machine Learning community. Despite its versatility and excellent performance, the optimization of large models via SGD still is a time-consuming…

Machine Learning · Computer Science 2025-12-01 Mauro DL Tosi , Martin Theobald

In this paper, we focus on approaches to parallelizing stochastic gradient descent (SGD) wherein data is farmed out to a set of workers, the results of which, after a number of updates, are then combined at a central master node. Although…

Machine Learning · Computer Science 2018-10-09 Nuwan Ferdinand , Stark Draper

Data and pipeline parallelism are key strategies for scaling neural network training across distributed devices, but their high communication cost necessitates co-located computing clusters with fast interconnects, limiting their…

In this paper we consider large-scale smooth optimization problems with multiple linear coupled constraints. Due to the non-separability of the constraints, arbitrary random sketching would not be guaranteed to work. Thus, we first…

Optimization and Control · Mathematics 2018-08-09 Ion Necoara , Martin Takac

To increase the training speed of distributed learning, recent years have witnessed a significant amount of interest in developing both synchronous and asynchronous distributed stochastic variance-reduced optimization methods. However, all…

Machine Learning · Computer Science 2022-08-30 Zhuqing Liu , Xin Zhang , Jia Liu

Quantum coherence allows the computation of an arbitrary number of distinct computational paths in parallel. Based on quantum parallelism it has been conjectured that exponential or even larger speedups of computations are possible. Here it…

High Energy Physics - Theory · Physics 2007-05-23 K. Svozil

Submodular function minimization is a fundamental optimization problem that arises in several applications in machine learning and computer vision. The problem is known to be solvable in polynomial time, but general purpose algorithms have…

Machine Learning · Computer Science 2015-02-10 Alina Ene , Huy L. Nguyen
‹ Prev 1 8 9 10 Next ›