A primal-dual Generalized Sequential algorithm achieves the first competitive ratio bound for online monotone DR-submodular maximization subject to linear packing constraints, matching the tight bound known for linear objectives.
Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains
2 Pith papers cite this work. Polarity classification is still indexing.
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 $(1-1/e)$ 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 $1/3$ 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.
fields
math.OC 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
OSPHG algorithm achieves sub-linear (1-1/e)-regret and sub-linear budget violation for online DR-submodular maximization with long-term budgets when W = o(T).
citing papers explorer
-
Competitive Algorithms for Online Budget-Constrained Continuous DR-Submodular Problems
A primal-dual Generalized Sequential algorithm achieves the first competitive ratio bound for online monotone DR-submodular maximization subject to linear packing constraints, matching the tight bound known for linear objectives.
-
Online Continuous DR-Submodular Maximization with Long-Term Budget Constraints
OSPHG algorithm achieves sub-linear (1-1/e)-regret and sub-linear budget violation for online DR-submodular maximization with long-term budgets when W = o(T).