DeepAI AI Chat
Log In Sign Up

Submodular Maximization with Optimal Approximation, Adaptivity and Query Complexity

by   Matthew Fahrbach, et al.

As a generalization of many classic problems in combinatorial optimization, submodular optimization has found a wide range of applications in machine learning (e.g., in feature engineering and active learning). For many large-scale optimization problems, we are often concerned with the adaptivity complexity of an algorithm, which quantifies the number of sequential rounds where polynomially-many independent function evaluations can be executed in parallel. While low adaptivity is ideal, it is not sufficient for a (distributed) algorithm to be efficient, since in many practical applications of submodular optimization the number of function evaluations becomes prohibitively expensive. Motivated by such applications, we study the adaptivity and query complexity of adaptive submodular optimization. Our main result is a distributed algorithm for maximizing a monotone submodular function with cardinality constraint k that achieves a (1-1/e-ε)-approximation in expectation. Furthermore, this algorithm runs in O((n)) adaptive rounds and makes O(n) calls to the function evaluation oracle in expectation. All three of these guarantees are optimal, and the query complexity is substantially less than in previous works. Finally, to show the generality of our simple algorithm and techniques, we extend our results to the submodular cover problem.


page 1

page 2

page 3

page 4


Non-monotone Submodular Maximization with Nearly Optimal Adaptivity Complexity

As a generalization of many classic problems in combinatorial optimizati...

Submodular Optimization in the MapReduce Model

Submodular optimization has received significant attention in both pract...

Categorical Feature Compression via Submodular Optimization

In the era of big data, learning from categorical features with very lar...

Comments on the proof of adaptive submodular function minimization

We point out an issue with Theorem 5 appearing in "Group-based active qu...

Best of Both Worlds: Practical and Theoretically Optimal Submodular Maximization in Parallel

For the problem of maximizing a monotone, submodular function with respe...

Adaptive Sampling for Fast Constrained Maximization of Submodular Function

Several large-scale machine learning tasks, such as data summarization, ...

An Approximation Algorithm for Risk-averse Submodular Optimization

We study the problem of incorporating risk while making combinatorial de...