资源分类
》 资源 》论文》Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees

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

2020-03-19 | |  46 |   44 |   0

Abstract

We present a novel way of generating Lyapunov functions for proving linear convergence rates of first-order optimization methods. Our approach provably obtains the fastest linear convergence rate that can be verified by a quadratic Lyapunov function (with given states), and only relies on solving a small-sized semidefinite program. Our approach combines the advantages of performance estimation problems (PEP, due to Drori & Teboulle (2014)) and integral quadratic constraints (IQC, due to Lessard et al. (2016)), and relies on convex interpolation (due to Taylor et al. (2017c;b)).

上一篇：ADMM and Accelerated ADMM as Continuous Dynamical Systems

下一篇：Adaptive Three Operator Splitting

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...