arxivst stuff from arxiv that you should probably bookmark

Conditional Accelerated Lazy Stochastic Gradient Descent

Abstract · Mar 16, 2017 22:15 ·

cs-lg stat-ml

Arxiv Abstract

  • Guanghui Lan
  • Sebastian Pokutta
  • Yi Zhou
  • Daniel Zink

In this work we introduce a conditional accelerated lazy stochastic gradient descent algorithm with optimal number of calls to a stochastic first-order oracle and convergence rate $O\left(\frac{1}{\varepsilon^2}\right)$ improving over the projection-free, Online Frank-Wolfe based stochastic gradient descent of Hazan and Kale [2012] with convergence rate $O\left(\frac{1}{\varepsilon^4}\right)$.

Read the paper (pdf) »