Robustness meets algorithms
<jats:p>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 ea...
Main Authors: | Diakonikolas, Ilias, Kamath, Gautam, Kane, Daniel M, Li, Jerry, Moitra, Ankur, Stewart, Alistair |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | English |
Published: |
Association for Computing Machinery (ACM)
2021
|
Online Access: | https://hdl.handle.net/1721.1/135599 |
Similar Items
-
Robust Estimators in High-Dimensions Without the Computational Intractability
by: Diakonikolas, Ilias, et al.
Published: (2020) -
Robust Estimators in High Dimensions without the Computational Intractability
by: Diakonikolas, Ilias, et al.
Published: (2018) -
Robustly Learning a Gaussian: Getting Optimal Error, Efficiently
by: Stewart, Alistair, et al.
Published: (2018) -
Robustly Learning General Mixtures of Gaussians
by: Liu, Allen, et al.
Published: (2023) -
Settling the Robust Learnability of Mixtures of Gaussians
by: Liu, Allen, et al.
Published: (2022)