Robustness meets algorithms
Name
3453935.pdf
Description
Published version
Size
2.7 MB
Format
Adobe PDF
Checksum (MD5)
8bed65a3b2879e35630d5af1d085ee67
Author(s)
Diakonikolas, Ilias
Kamath, Gautam
Kane, Daniel M
Li, Jerry
Moitra, Ankur
Stewart, Alistair
Date Issued
2021
Journal
Communications of the ACM
Publisher
Association for Computing Machinery (ACM)
Version
Final published version
Abstract
In every corner of machine learning and statistics, there is a need for estimators that work not just in an idealized model, but even when their assumptions are violated. Unfortunately, in high dimensions, being provably robust and being efficiently computable are often at odds with each other.
We give the first efficient algorithm for estimating the parameters of a high-dimensional Gaussian that is able to tolerate a constant fraction of corruptions that is independent of the dimension. Prior to our work, all known estimators either needed time exponential in the dimension to compute or could tolerate only an inverse-polynomial fraction of corruptions. Not only does our algorithm bridge the gap between robustness and algorithms, but also it turns out to be highly practical in a variety of settings.
We give the first efficient algorithm for estimating the parameters of a high-dimensional Gaussian that is able to tolerate a constant fraction of corruptions that is independent of the dimension. Prior to our work, all known estimators either needed time exponential in the dimension to compute or could tolerate only an inverse-polynomial fraction of corruptions. Not only does our algorithm bridge the gap between robustness and algorithms, but also it turns out to be highly practical in a variety of settings.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3453935
