Probabilistic Line Searches for Stochastic Optimization


Conference Paper



In deterministic optimization, line searches are a standard tool ensuring stability and efficiency. Where only stochastic gradients are available, no direct equivalent has so far been formulated, because uncertain gradients do not allow for a strict sequence of decisions collapsing the search space. We construct a probabilistic line search by combining the structure of existing deterministic methods with notions from Bayesian optimization. Our method retains a Gaussian process surrogate of the univariate optimization objective, and uses a probabilistic belief over the Wolfe conditions to monitor the descent. The algorithm has very low computational cost, and no user-controlled parameters. Experiments show that it effectively removes the need to define a learning rate for stochastic gradient descent. [You can find the matlab research code under `attachments' below. The zip-file contains a minimal working example. The docstring in probLineSearch.m contains additional information. A more polished implementation in C++ will be published here at a later point. For comments and questions about the code please write to]

Author(s): Mahsereci, M. and Hennig, P.
Book Title: Advances in Neural Information Processing Systems 28
Pages: 181--189
Year: 2015
Editors: C. Cortes, N.D. Lawrence, D.D. Lee, M. Sugiyama and R. Garnett
Publisher: Curran Associates, Inc.

Department(s): Empirical Inference, Probabilistic Numerics
Research Project(s): Probabilistic Methods for Nonlinear Optimization
Bibtex Type: Conference Paper (inproceedings)

Event Name: 29th Annual Conference on Neural Information Processing Systems (NIPS 2015)
Event Place: Montreal, Canada
State: Published
Attachments: Matlab research code


  title = {Probabilistic Line Searches for Stochastic Optimization},
  author = {Mahsereci, M. and Hennig, P.},
  booktitle = {Advances in Neural Information Processing Systems 28},
  pages = {181--189},
  editors = {C. Cortes, N.D. Lawrence, D.D. Lee, M. Sugiyama and R. Garnett},
  publisher = {Curran Associates, Inc.},
  year = {2015},
  url = {}