English

Black Box Submodular Maximization: Discrete and Continuous Settings

Machine Learning 2020-03-03 v2 Data Structures and Algorithms Optimization and Control Machine Learning

Abstract

In this paper, we consider the problem of black box continuous submodular maximization where we only have access to the function values and no information about the derivatives is provided. For a monotone and continuous DR-submodular function, and subject to a bounded convex body constraint, we propose Black-box Continuous Greedy, a derivative-free algorithm that provably achieves the tight [(11/e)OPTϵ][(1-1/e)OPT-\epsilon] approximation guarantee with O(d/ϵ3)O(d/\epsilon^3) function evaluations. We then extend our result to the stochastic setting where function values are subject to stochastic zero-mean noise. It is through this stochastic generalization that we revisit the discrete submodular maximization problem and use the multi-linear extension as a bridge between discrete and continuous settings. Finally, we extensively evaluate the performance of our algorithm on continuous and discrete submodular objective functions using both synthetic and real data.

Keywords

Cite

@article{arxiv.1901.09515,
  title  = {Black Box Submodular Maximization: Discrete and Continuous Settings},
  author = {Lin Chen and Mingrui Zhang and Hamed Hassani and Amin Karbasi},
  journal= {arXiv preprint arXiv:1901.09515},
  year   = {2020}
}

Comments

Accepted to AISTATS 2020. First two authors contributed equally to this work

R2 v1 2026-06-23T07:23:40.777Z