NeurIPS 2020oral30 citations
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub M Tarnawski, Morteza Zadimoghaddam
Abstract
The task of maximizing a monotone submodular function under a cardinality constraint is at the core of many machine learning and data mining applications, including data summarization, sparse regression and coverage problems. We study this classic problem in the fully dynamic setting, where elements can be both inserted and removed. Our main result is a randomized algorithm that maintains an efficient data structure with a poly-logarithmic amortized update time and yields a $(1/2-epsilon)$-approximate solution. We complement our theoretical analysis with an empirical study of the performance of our algorithm.
BibTeX
@inproceedings{NEURIPS2020_9715d044,
author = {Lattanzi, Silvio and Mitrovi\'{c}, Slobodan and Norouzi-Fard, Ashkan and Tarnawski, Jakub M and Zadimoghaddam, Morteza},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {12923--12933},
publisher = {Curran Associates, Inc.},
title = {Fully Dynamic Algorithm for Constrained Submodular Optimization},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/9715d04413f296eaf3c30c47cec3daa6-Paper.pdf},
volume = {33},
year = {2020}
}