Regularized Submodular Maximization at Scale

by   Ehsan Kazemi, et al.

In this paper, we propose scalable methods for maximizing a regularized submodular function f = g - ℓ expressed as the difference between a monotone submodular function g and a modular function ℓ. 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 f 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 k-cardinality constraint. It returns a solution S with the guarantee that f(S)≥(ϕ^-2-ϵ) · g(OPT)-ℓ (OPT), where ϕ is the golden ratio. Furthermore, we develop the first distributed algorithm that returns a solution S with the guarantee that E[f(S)] ≥ (1-ϵ) [(1-e^-1) · g(OPT)-ℓ(OPT)] in O(1/ ϵ) 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 ℓ is zero, improves the memory and communication complexity of the existing work by a factor of O(1/ ϵ) 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.


Regularized Non-monotone Submodular Maximization

In this paper, we present a thorough study of maximizing a regularized n...

On Maximizing Sums of Non-monotone Submodular and Linear Functions

We study the problem of Regularized Unconstrained Submodular Maximizatio...

A Parameterized Family of Meta-Submodular Functions

Submodular function maximization has found a wealth of new applications ...

Re-ranking Based Diversification: A Unifying View

We analyze different re-ranking algorithms for diversification and show ...

Submodular Maximization Through Barrier Functions

In this paper, we introduce a novel technique for constrained submodular...

Distributed Submodular Maximization

Many large-scale machine learning problems--clustering, non-parametric l...

Please sign up or login with your details

Forgot password? Click here to reset