6
36

Regularized Submodular Maximization at Scale

Abstract

In this paper, we propose scalable methods for maximizing a regularized submodular function f=gf = g - \ell expressed as the difference between a monotone submodular function gg and a modular function \ell. Indeed, submodularity is inherently related to the notions of diversity, coverage, and representativeness. In particular, finding the mode of many popular probabilistic models of diversity, such as determinantal point processes, submodular probabilistic models, and strongly log-concave distributions, involves maximization of (regularized) submodular functions. Since a regularized function ff can potentially take on negative values, the classic theory of submodular maximization, which heavily relies on the non-negativity assumption of submodular functions, may not be applicable. To circumvent this challenge, we develop the first one-pass streaming algorithm for maximizing a regularized submodular function subject to a kk-cardinality constraint. It returns a solution SS with the guarantee that f(S)(ϕ2ϵ)g(OPT)(OPT)f(S)\geq(\phi^{-2}-\epsilon) \cdot g(OPT)-\ell (OPT), where ϕ\phi is the golden ratio. Furthermore, we develop the first distributed algorithm that returns a solution SS with the guarantee that E[f(S)](1ϵ)[(1e1)g(OPT)(OPT)]\mathbb{E}[f(S)] \geq (1-\epsilon) [(1-e^{-1}) \cdot g(OPT)-\ell(OPT)] in O(1/ϵ)O(1/ \epsilon) rounds of MapReduce computation, without keeping multiple copies of the entire dataset in each round (as it is usually done). We should highlight that our result, even for the unregularized case where the modular term \ell is zero, improves the memory and communication complexity of the existing work by a factor of O(1/ϵ)O(1/ \epsilon) while arguably provides a simpler distributed algorithm and a unifying analysis. We also empirically study the performance of our scalable methods on a set of real-life applications, including finding the mode of distributions, data summarization, and product recommendation.

View on arXiv
Comments on this paper