AISTATS 2016poster340 citations

A Linearly-Convergent Stochastic L-BFGS Algorithm

Philipp Moritz, Robert Nishihara, Michael Jordan

Abstract

We propose a new stochastic L-BFGS algorithm and prove a linear convergence rate for strongly convex and smooth functions. Our algorithm draws heavily from a recent stochastic variant of L-BFGS proposed in Byrd et al. (2014) as well as a recent approach to variance reduction for stochastic gradient descent from Johnson and Zhang (2013). We demonstrate experimentally that our algorithm performs well on large-scale convex and non-convex optimization problems, exhibiting linear convergence and rapidly solving the optimization problems to high levels of precision. Furthermore, we show that our algorithm performs well for a wide-range of step sizes, often differing by several orders of magnitude.

BibTeX
@InProceedings{pmlr-v51-moritz16,
  title = 	 {A Linearly-Convergent Stochastic L-BFGS Algorithm},
  author = 	 {Moritz, Philipp and Nishihara, Robert and Jordan, Michael},
  booktitle = 	 {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {249--258},
  year = 	 {2016},
  editor = 	 {Gretton, Arthur and Robert, Christian C.},
  volume = 	 {51},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Cadiz, Spain},
  month = 	 {09--11 May},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v51/moritz16.pdf},
  url = 	 {https://proceedings.mlr.press/v51/moritz16.html},
  abstract = 	 {We propose a new stochastic L-BFGS algorithm and prove a linear convergence rate for strongly convex and smooth functions. Our algorithm draws heavily from a recent stochastic variant of L-BFGS proposed in Byrd et al. (2014) as well as a recent approach to variance reduction for stochastic gradient descent from Johnson and Zhang (2013). We demonstrate experimentally that our algorithm performs well on large-scale convex and non-convex optimization problems, exhibiting linear convergence and rapidly solving the optimization problems to high levels of precision. Furthermore, we show that our algorithm performs well for a wide-range of step sizes, often differing by several orders of magnitude.}
}
A Linearly-Convergent Stochastic L-BFGS Algorithm · AISTATS 2016