Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains
Abstract
Submodular continuous functions are a category of (generally) non-convex/non-concave functions with a wide spectrum of applications. We characterize these functions and demonstrate that they can be maximized efficiently with approximation guarantees. Specifically, i) We introduce the weak DR property that gives a unified characterization of submodularity for all set, integer-lattice and continuous functions; ii) for maximizing monotone DR-submodular continuous functions under general down-closed convex constraints, we propose a Frank-Wolfe variant with approximation guarantee, and sub-linear convergence rate; iii) for maximizing general non-monotone submodular continuous functions subject to box constraints, we propose a DoubleGreedy algorithm with approximation guarantee. Submodular continuous functions naturally find applications in various real-world settings, including influence and revenue maximization with continuous assignments, sensor energy management, multi-resolution data summarization, facility location, etc. Experimental results show that the proposed algorithms efficiently generate superior solutions compared to baseline algorithms.
Cite
@article{arxiv.1606.05615,
title = {Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains},
author = {Andrew An Bian and Baharan Mirzasoleiman and Joachim M. Buhmann and Andreas Krause},
journal= {arXiv preprint arXiv:1606.05615},
year = {2019}
}
Comments
Appears in the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017