Katyusha: The First Direct Acceleration of Stochastic Gradient Methods

03/18/2016 ∙ by Zeyuan Allen-Zhu, et al. ∙ 0

Nesterov's momentum trick is famously known for accelerating gradient descent, and has been proven useful in building fast iterative algorithms. However, in the stochastic setting, counterexamples exist and prevent Nesterov's momentum from providing similar acceleration, even if the underlying problem is convex. We introduce Katyusha, a direct, primal-only stochastic gradient method to fix this issue. It has a provably accelerated convergence rate in convex (off-line) stochastic optimization. The main ingredient is Katyusha momentum, a novel "negative momentum" on top of Nesterov's momentum. It can be incorporated into a variance-reduction based algorithm and speed it up, both in terms of sequential and parallel performance. Since variance reduction has been successfully applied to a growing list of practical problems, our paper suggests that in each of such cases, one could potentially try to give Katyusha a hug.



There are no comments yet.


page 15

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.