Approximate optimization of convex functions with outlier noise
Anindya De, Sanjeev Khanna, Huan Li, Hesam Nikpey
Abstract
We study the problem of minimizing a convex function given by a zeroth order oracle that is possibly corrupted by {\em outlier noise}. Specifically, we assume the function values at some points of the domain are corrupted arbitrarily by an adversary, with the only restriction being that the total volume of corrupted points is bounded. The goal then is to find a point close to the function's minimizer using access to the corrupted oracle. We first prove a lower bound result showing that, somewhat surprisingly, one cannot hope to approximate the minimizer {\em nearly as well} as one might expect, even if one is allowed {\em an unbounded number} of queries to the oracle. Complementing this negative result, we then develop an efficient algorithm that outputs a point close to the minimizer of the convex function, where the specific distance matches {\em exactly}, up to constant factors, the distance bound shown in our lower bound result.
BibTeX
@inproceedings{
de2021approximate,
title={Approximate optimization of convex functions with outlier noise},
author={Anindya De and Sanjeev Khanna and Huan Li and Hesam Nikpey},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=r6Khc1Lq9z1}
}