English

Guarantees for Greedy Maximization of Non-submodular Functions with Applications

Discrete Mathematics 2019-05-15 v4 Artificial Intelligence Data Structures and Algorithms Machine Learning Optimization and Control

Abstract

We investigate the performance of the standard Greedy algorithm for cardinality constrained maximization of non-submodular nondecreasing set functions. While there are strong theoretical guarantees on the performance of Greedy for maximizing submodular functions, there are few guarantees for non-submodular ones. However, Greedy enjoys strong empirical performance for many important non-submodular functions, e.g., the Bayesian A-optimality objective in experimental design. We prove theoretical guarantees supporting the empirical performance. Our guarantees are characterized by a combination of the (generalized) curvature α\alpha and the submodularity ratio γ\gamma. In particular, we prove that Greedy enjoys a tight approximation guarantee of 1α(1eγα)\frac{1}{\alpha}(1- e^{-\gamma\alpha}) for cardinality constrained maximization. In addition, we bound the submodularity ratio and curvature for several important real-world objectives, including the Bayesian A-optimality objective, the determinantal function of a square submatrix and certain linear programs with combinatorial constraints. We experimentally validate our theoretical findings for both synthetic and real-world applications.

Keywords

Cite

@article{arxiv.1703.02100,
  title  = {Guarantees for Greedy Maximization of Non-submodular Functions with Applications},
  author = {Andrew An Bian and Joachim M. Buhmann and Andreas Krause and Sebastian Tschiatschek},
  journal= {arXiv preprint arXiv:1703.02100},
  year   = {2019}
}

Comments

published at ICML 2017. First author is now known as Yatao Bian <ybian@inf.ethz.ch>. ORCID: https://orcid.org/0000-0002-2368-4084

R2 v1 2026-06-22T18:37:41.278Z