TY - GEN
T1 - Online submodular minimization for combinatorial structures
AU - Jegelka, Stefanie
AU - Bilmes, Jeff
PY - 2011
Y1 - 2011
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=80053439900&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:80053439900
SN - 9781450306195
T3 - Proceedings of the 28th International Conference on Machine Learning, ICML 2011
SP - 345
EP - 352
BT - Proceedings of the 28th International Conference on Machine Learning, ICML 2011
T2 - 28th International Conference on Machine Learning, ICML 2011
Y2 - 28 June 2011 through 2 July 2011
ER -