Empirical Inference

Online submodular minimization for combinatorial structures

2011

Conference Paper

ei


Most results for online decision problems with structured concepts, such as trees or cuts, assume linear costs. In many settings, however, nonlinear costs are more realistic. Owing to their non-separability, these lead to much harder optimization problems. Going beyond linearity, we address online approximation algorithms for structured concepts that allow the cost to be submodular, i.e., nonseparable. In particular, we show regret bounds for three Hannan-consistent strategies that capture different settings. Our results also tighten a regret bound for unconstrained online submodular minimization.

Author(s): Jegelka, S. and Bilmes, J.
Pages: 345-352
Year: 2011
Month: July
Day: 0
Editors: Getoor, L. , T. Scheffer
Publisher: International Machine Learning Society

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: 28th International Conference on Machine Learning (ICML 2011)
Event Place: Bellevue, WA, USA

Address: Madison, WI, USA
Digital: 0
ISBN: 978-1-450-30619-5

Links: PDF
PDF
Web

BibTex

@inproceedings{JegelkaB2011_3,
  title = {Online submodular minimization for combinatorial structures},
  author = {Jegelka, S. and Bilmes, J.},
  pages = {345-352},
  editors = {Getoor, L. , T. Scheffer},
  publisher = {International Machine Learning Society},
  address = {Madison, WI, USA},
  month = jul,
  year = {2011},
  doi = {},
  month_numeric = {7}
}