摘要: Coordinate descent algorithms solve optimization problems by successively performing approximate minimization along coordinate directions or hyperplanes. They have been used in applications for many years, and their popularity continues to grow because of usefulness data analysis, machine learning, other areas current interest. This paper describes the fundamentals approach, together with variants extensions convergence properties, mostly reference convex objectives. We pay particular attention a certain problem structure that arises frequently learning applications, showing efficient implementations accelerated are possible this type. also present some parallel discuss properties under several models execution.
acm.org
core.ac.uk
arxiv-vanity.com
springer.com
optimization-online.org 
arxiv.org 参考文章(55)
Yin Tat Lee, Aaron Sidford, Efficient Accelerated Coordinate Descent Methods and Faster Algorithms for Solving Linear Systems 2013 IEEE 54th Annual Symposium on Foundations of Computer Science. pp. 147- 156 ,(2013) , 10.1109/FOCS.2013.24
Martin Takac, Jonathan Terhorst, Sanjay Krishnan, Virginia Smith, Martin Jaggi, Thomas Hofmann, Michael I Jordan, Communication-Efficient Distributed Dual Coordinate Ascent neural information processing systems. ,vol. 27, pp. 3068- 3076 ,(2014)
Shai Shalev-Shwartz, Ambuj Tewari, Stochastic Methods for l 1 -regularized Loss Minimization Journal of Machine Learning Research. ,vol. 12, pp. 1865- 1892 ,(2011)
I︠u︡. E. Nesterov, Introductory Lectures on Convex Optimization: A Basic Course ,(2014)
John C. Platt, Fast training of support vector machines using sequential minimal optimization Advances in kernel methods. pp. 185- 208 ,(1999)
P. Tseng, Convergence of a Block Coordinate Descent Method for Nondifferentiable Minimization Journal of Optimization Theory and Applications. ,vol. 109, pp. 475- 494 ,(2001) , 10.1023/A:1017501703105
Boris T Poljak, Introduction to optimization Optimization Software, Publications Division. ,(1987)
Jakub Mareček, Peter Richtárik, Martin Takáč, Distributed Block Coordinate Descent for Minimizing Partially Separable Functions Numerical Analysis and Optimization. pp. 261- 288 ,(2015) , 10.1007/978-3-319-17689-5_11
John N. Tsitsiklis, Dimitri P. Bertsekas, Parallel and Distributed Computation: Numerical Methods ,(1989)
Stephen J. Wright, Ji Liu, An Accelerated Randomized Kaczmarz Algorithm arXiv: Numerical Analysis. ,(2013)