NIPS Proceedingsβ

Beyond Convexity: Online Submodular Minimization

Part of: Advances in Neural Information Processing Systems 22 (NIPS 2009)

[PDF] [BibTeX]

Authors

Abstract

We consider an online decision problem over a discrete space in which the loss function is submodular. We give algorithms which are computationally efficient and are Hannan-consistent in both the full information and bandit settings.