Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity

Abstract

Submodular maximization is a general optimization problem with a wide range of applications in machine learning (e.g., active learning, clustering, and feature selection). In large-scale optimization, the parallel running time of an algorithm is governed by its adaptivity, which measures the number of sequential rounds needed if the algorithm can execute polynomially-many independent oracle queries in parallel. While low adaptivity is ideal, it is not sufficient for an algorithm to be efficient in practice -- there are many applications of distributed submodular optimization where the number of function evaluations becomes prohibitively expensive. Motivated by these applications, we study the adaptivity and query complexity of submodular maximization. In this paper, we give the first constant-factor approximation algorithm for maximizing a non-monotone submodular function subject to a cardinality constraint $k$ that runs in $O(\log (n))$ adaptive rounds and makes $O(n\log (k))$ oracle queries in expectation. In our empirical study, we use three real-world applications to compare our algorithm with several benchmarks for non-monotone submodular maximization. The results demonstrate that our algorithm finds competitive solutions using significantly fewer rounds and queries.

19 pages, 8 figures. This version fixes a bug in the threshold sampling algorithm that implicitly assumed monotonicity. All original results hold

Cited by in corpus (9)

• Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias
• Fast Adaptive Non-Monotone Submodular Maximization Subject to a Knapsack Constraint
• Batch greedy maximization of non-submodular functions: Guarantees and applications to experimental design
• Deterministic Approximation for Submodular Maximization over a Matroid in Nearly Linear Time
• Practical and Parallelizable Algorithms for Non-Monotone Submodular Maximization with Size Constraint
• Guarantees of Stochastic Greedy Algorithms for Non-monotone Submodular Maximization with Cardinality Constraint
• The Power of Randomization: Efficient and Effective Algorithms for Constrained Submodular Maximization
• A polynomial lower bound on adaptive complexity of submodular maximization
• Adaptive Sampling for Fast Constrained Maximization of Submodular Function