BriefGPT.xyz
Mar, 2017
马尔科夫链提升和分布式ADMM
Markov Chain Lifting and Distributed ADMM
HTML
PDF
Guilherme França, José Bento
TL;DR
通过lifting操作，对于一类二次目标函数，分布式ADMM算法可以被看作梯度下降算法的lifting，从而提高其稳态收敛速度并得到最优参数调整。我们猜测这个增益总是存在的，而不像马尔科夫链一样有时只提供微弱加速。
Abstract
The time to converge to the steady state of a finite
markov chain
can be greatly reduced by a
lifting operation
, which creates a new
markov chain
→