资源分类
》 资源 》论文》ADMM and Accelerated ADMM as Continuous Dynamical Systems

ADMM and Accelerated ADMM as Continuous Dynamical Systems

2020-03-19 | |  44 |   40 |   0

Abstract

Recently, there has been an increasing interest in using tools from dynamical systems to analyze the behavior of simple optimization algorithms such as gradient descent and accelerated variants. This paper strengthens such connections by deriving the differential equations that model the continuous limit of the sequence of iterates generated by the alternating direction method of multipliers, as well as an accelerated variant. We employ the direct method of Lyapunov to analyze the stability of critical points of the dynamical systems and to obtain associated convergence rates.

上一篇：Unbiased Objective Estimation in Predictive Optimization

下一篇：Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...