资源分类
》 资源 》论文》Sharpness, Restart and Acceleration

Sharpness, Restart and Acceleration

2020-02-10 | |  42 |   40 |   0

Abstract 

The image.png inequality shows that sharpness bounds on the minimum of convex optimization problems hold almost generically. Sharpness directly controls the performance of restart schemes, as observed by Nemirovskii and Nesterov [1985]. The constants quantifying error bounds are of course unobservable, but we show that optimal restart strategies are robust, and searching for the best scheme only increases the complexity by a logarithmic factor compared to the optimal bound. Overall then, restart schemes generically accelerate accelerated methods.

上一篇：Doubly Stochastic Variational Inference for Deep Gaussian Processes

下一篇：The Numerics of GANs

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...