Fixed-Point Algorithms for Learning Determinantal Point Processes
Abstract
Determinantal point processes (DPPs) offer an elegant tool for encoding probabilities over subsets of a ground set. Discrete DPPs are parametrized by a positive semidefinite matrix (called the DPP kernel), and estimating this kernel is key to learning DPPs from observed data. We consider the task of learning the DPP kernel, and develop for it a surprisingly simple yet effective new algorithm. Our algorithm offers the following benefits over previous approaches: (a) it is much simpler; (b) it yields equally good and sometimes even better local maxima; and (c) it runs an order of magnitude faster on large problems. We present experimental results on both real and simulated data to illustrate the numerical performance of our technique.
Cite
Text
Mariet and Sra. "Fixed-Point Algorithms for Learning Determinantal Point Processes." International Conference on Machine Learning, 2015.Markdown
[Mariet and Sra. "Fixed-Point Algorithms for Learning Determinantal Point Processes." International Conference on Machine Learning, 2015.](https://mlanthology.org/icml/2015/mariet2015icml-fixedpoint/)BibTeX
@inproceedings{mariet2015icml-fixedpoint,
title = {{Fixed-Point Algorithms for Learning Determinantal Point Processes}},
author = {Mariet, Zelda and Sra, Suvrit},
booktitle = {International Conference on Machine Learning},
year = {2015},
pages = {2389-2397},
volume = {37},
url = {https://mlanthology.org/icml/2015/mariet2015icml-fixedpoint/}
}