English

Non-Smooth, H\"older-Smooth, and Robust Submodular Maximization

Optimization and Control 2023-09-29 v3 Data Structures and Algorithms

Abstract

We study the problem of maximizing a continuous DR-submodular function that is not necessarily smooth. We prove that the continuous greedy algorithm achieves an [(11/e)\OPTϵ][(1-1/e)\OPT-\epsilon] guarantee when the function is monotone and H\"older-smooth, meaning that it admits a H\"older-continuous gradient. For functions that are non-differentiable or non-smooth, we propose a variant of the mirror-prox algorithm that attains an [(1/2)\OPTϵ][(1/2)\OPT-\epsilon] guarantee. We apply our algorithmic frameworks to robust submodular maximization and distributionally robust submodular maximization under Wasserstein ambiguity. In particular, the mirror-prox method applies to robust submodular maximization to obtain a single feasible solution whose value is at least (1/2)\OPTϵ(1/2)\OPT-\epsilon. For distributionally robust maximization under Wasserstein ambiguity, we deduce and work over a submodular-convex maximin reformulation whose objective function is H\"older-smooth, for which we may apply both the continuous greedy and the mirror-prox algorithms.

Keywords

Cite

@article{arxiv.2210.06061,
  title  = {Non-Smooth, H\"older-Smooth, and Robust Submodular Maximization},
  author = {Duksang Lee and Nam Ho-Nguyen and Dabeen Lee},
  journal= {arXiv preprint arXiv:2210.06061},
  year   = {2023}
}
R2 v1 2026-06-28T03:25:20.651Z