Robustness meets algorithms
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.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Apr 26, 2021
- Source ID
- 10.1145/3453935
Entities
People
- Alistair Stewart
- Ankur Moitra
- Daniel M. Kane
- Gautam Kamath
- Ilias Diakonikolas
- Jerry Li
Organizations
- Alfred P. Sloan Foundation
- David and Lucile Packard Foundation
- Massachusetts Institute of Technology
- Microsoft
- National Science Foundation
- Office of Naval Research
- University of California, San Diego
- University of Waterloo
- University of Wisconsin–Madison