by ,
Abstract:
Solving stochastic optimization problems under partial observability, where one needs to adaptively make decisions with uncertain outcomes, is a fundamental but notoriously difficult challenge. In this paper, we introduce the concept of adaptive submodularity, generalizing submodular set functions to adaptive policies. We prove that if a problem satisfies this property, a simple adaptive greedy algorithm is guaranteed to be competitive with the optimal policy. In addition to providing performance guarantees for both stochastic maximization and coverage, adaptive submodularity can be exploited to drastically speed up the greedy algorithm by using lazy evaluations. We illustrate the usefulness of the concept by giving several examples of adaptive submodular objectives arising in diverse applications including sensor placement, viral marketing and active learning. Proving adaptive submodularity for these problems allows us to recover existing results in these applications as special cases, improve approximation guarantees and handle natural generalizations.
Reference:
Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization D. Golovin, A. KrauseIn Journal of Artificial Intelligence Research (JAIR), volume 42, 2011IJCAI-JAIR Best Paper Award 2013
Bibtex Entry:
@article{golovin11adaptive,
	Author = {Daniel Golovin and Andreas Krause},
	Journal = {Journal of Artificial Intelligence Research (JAIR)},
	Pages = {427-486},
	Title = {Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization},
	Volume = {42},
	Year = {2011}}