Back
Online submodular minimization for combinatorial structures
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.
@inproceedings{JegelkaB2011_3, title = {Online submodular minimization for combinatorial structures}, 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. }, pages = {345-352}, editors = {Getoor, L. , T. Scheffer}, publisher = {International Machine Learning Society}, address = {Madison, WI, USA}, month = jul, year = {2011}, slug = {jegelkab2011_3}, author = {Jegelka, S. and Bilmes, J.}, month_numeric = {7} }