Web: http://arxiv.org/abs/2201.11489

Jan. 28, 2022, 2:11 a.m. | Ohad Shamir

cs.LG updates on arXiv.org arxiv.org

The phenomenon of benign overfitting, where a predictor perfectly fits noisy
training data while attaining low expected loss, has received much attention in
recent years, but still remains not fully understood beyond simple linear
regression setups. In this paper, we show that for regression, benign
overfitting is "biased" towards certain types of problems, in the sense that
its existence on one learning problem excludes its existence on other learning
problems. On the negative side, we use this to argue that …

arxiv bias overfitting

More from arxiv.org / cs.LG updates on arXiv.org

Director, Data Engineering and Architecture

@ Chainalysis | California | New York | Washington DC | Remote - USA

Deep Learning Researcher

@ Topaz Labs | Dallas, TX

Sr Data Engineer (Contractor)

@ SADA | US - West

Senior Cloud Database Administrator

@ Findhelp | Remote

Senior Data Analyst

@ System1 | Remote

Speech Machine Learning Research Engineer

@ Samsung Research America | Mountain View, CA