English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Online submodular minimization for combinatorial structures

MPS-Authors
/persons/resource/persons83994

Jegelka,  S
Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society;

/persons/resource/persons75286

Bilmes,  J.
Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society;

External Resource
No external resources are shared
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

Jegelka, S., & Bilmes, J. (2011). Online submodular minimization for combinatorial structures. In 28th International Conference on Machine Learning (ICML 2011) (pp. 345-352).


Cite as: http://hdl.handle.net/11858/00-001M-0000-0010-75BD-D
Abstract
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.