Online Non-Monotone DR-Submodular Maximization
Résumé
In this paper, we study fundamental problems of maximizing DR-submodular continuous functions that have real-world applications in the domain of machine learning, economics, operations research and communication systems. It captures a subclass of non-convex optimization that provides both theoretical and practical guarantees. Here, we focus on minimizing regret for online arriving non-monotone DRsubmodular functions over down-closed and general convex sets.
First, we present an online algorithm that achieves a 1/e-approximation ratio with the regret of O(T3/4) for maximizing DR-submodular functions over any down-closed convex set. Note that, the approximation ratio of 1/e matches the best-known offline guarantee. Next, we give an online algorithm that achieves an approximation guarantee (depending on the search space) for the problem of maximizing non-monotone continuous DR-submodular functions over a general convex set (not necessarily downclosed). Finally we run experiments to verify the performance of our algorithms on problems arising in machine learning domain with the real-world datasets.
Domaines
Recherche opérationnelle [math.OC]Origine | Fichiers produits par l'(les) auteur(s) |
---|