Faster and More Dynamic Maximum Flow by Incremental Breadth-First Search

  • Andrew V. Goldberg
  • Sagi Hed
  • Haim Kaplan
  • Pushmeet Kohli
  • Robert E. Tarjan
  • Renato F. Werneck
Conference paper

DOI: 10.1007/978-3-662-48350-3_52

Part of the Lecture Notes in Computer Science book series (LNCS, volume 9294)
Cite this paper as:
Goldberg A.V., Hed S., Kaplan H., Kohli P., Tarjan R.E., Werneck R.F. (2015) Faster and More Dynamic Maximum Flow by Incremental Breadth-First Search. In: Bansal N., Finocchi I. (eds) Algorithms - ESA 2015. Lecture Notes in Computer Science, vol 9294. Springer, Berlin, Heidelberg

Abstract

We introduce the Excesses Incremental Breadth-First Search (Excesses IBFS) algorithm for maximum flow problems. We show that Excesses IBFS has the best overall practical performance on real-world instances, while maintaining the same polynomial running time guarantee of O(mn2) as IBFS, which it generalizes. Some applications, such as video object segmentation, require solving a series of maximum flow problems, each only slightly different than the previous. Excesses IBFS naturally extends to this dynamic setting and is competitive in practice with other dynamic methods.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Andrew V. Goldberg
    • 1
  • Sagi Hed
    • 2
  • Haim Kaplan
    • 2
  • Pushmeet Kohli
    • 3
  • Robert E. Tarjan
    • 4
  • Renato F. Werneck
    • 1
  1. 1.Amazon.com Inc.SeattleUSA
  2. 2.School of Computer ScienceTel Aviv UniversityTel AvivIsrael
  3. 3.Microsoft ResearchCambridgeUK
  4. 4.Department of Computer SciencePrinceton University and Intertrust TechnologiesPrincetonUSA

Personalised recommendations