Does data interpolation contradict statistical optimality?
© 2019 by the author(s). We show that classical learning methods interpolating the training data can achieve optimal rates for the problems of nonparametric regression and prediction with square loss.
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
International Machine Learning Society,
2021-12-08T13:51:14Z.
|
| Subjects: | |
| Online Access: | Get fulltext |