Horizontally Scalable Submodular Maximization
Abstract
A variety of large-scale machine learning problems can be cast as instances of constrained submodular maximization. Existing approaches for distributed submodular maximization have a critical drawback: The capacity - number of instances that can fit in memory - must grow with the data set size. In practice, while one can provision many machines, the capacity of each machine is limited by physical constraints. We propose a truly scalable approach for distributed submodular maximization under fixed capacity. The proposed framework applies to a broad class of algorithms and constraints and provides theoretical guarantees on the approximation factor for any available capacity. We empirically evaluate the proposed algorithm on a variety of data sets and demonstrate that it achieves performance competitive with the centralized greedy solution.
Cite
@article{arxiv.1605.09619,
title = {Horizontally Scalable Submodular Maximization},
author = {Mario Lucic and Olivier Bachem and Morteza Zadimoghaddam and Andreas Krause},
journal= {arXiv preprint arXiv:1605.09619},
year = {2016}
}