Optimal distributed online prediction using mini-batches

Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, Lin Xiao

Research output: Contribution to journalArticlepeer-review

302 Scopus citations

Abstract

Online prediction methods are typically presented as serial algorithms running on a single processor. However, in the age of web-scale prediction problems, it is increasingly common to encounter situations where a single processor cannot keep up with the high rate at which inputs arrive. In this work, we present the distributed mini-batch algorithm, a method of converting many serial gradient-based online prediction algorithms into distributed algorithms. We prove a regret bound for this method that is asymptotically optimal for smooth convex loss functions and stochastic inputs. Moreover, our analysis explicitly takes into account communication latencies between nodes in the distributed environment. We show how our method can be used to solve the closely-related distributed stochastic optimization problem, achieving an asymptotically linear speed-up over multiple processors. Finally, we demonstrate the merits of our approach on a web-scale online prediction problem.

Original languageEnglish
Pages (from-to)165-202
Number of pages38
JournalJournal of Machine Learning Research
Volume13
StatePublished - Jan 2012
Externally publishedYes

Keywords

  • Convex optimization
  • Distributed computing
  • Online learning
  • Regret bounds
  • Stochastic optimization

Fingerprint

Dive into the research topics of 'Optimal distributed online prediction using mini-batches'. Together they form a unique fingerprint.

Cite this