An asynchronous parallel stochastic coordinate descent algorithm
An asynchronous parallel stochastic coordinate descent algorithm
复制标题
DOI:
10.5555/2789272.2789282
复制
发表时间:
2013-11
期刊:
影响因子:
--
通讯作者:
Ji Liu;Stephen J. Wright;C. Ré;Victor Bittorf;Srikrishna Sridhar
中科院分区:
文献类型:
--
作者:
Ji Liu;Stephen J. Wright;C. Ré;Victor Bittorf;Srikrishna Sridhar
We describe an asynchronous parallel stochastic coordinate descent algorithm for minimizing smooth unconstrained or separably constrained functions. The method achieves a linear convergence rate on functions that satisfy an essential strong convexity property and a sublinear rate (1/K) on general convex functions. Near-linear speedup on a multicore system can be expected if the number of processors is O(n1/2) in unconstrained optimization and O(n1/4) in the separable-constrained case, where n is the number of variables. We describe results from implementation on 40-core processors.