Abstract
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.
| Original language | English |
|---|---|
| Pages (from-to) | 1611-1619 |
| Number of pages | 9 |
| Journal | Proceedings of Machine Learning Research |
| Volume | 89 |
| Publication status | Published - 1 Jan 2019 |
| Externally published | Yes |
| Event | 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019 - Naha, Japan Duration: 16 Apr 2019 → 18 Apr 2019 |
Fingerprint
Dive into the research topics of 'Does data interpolation contradict statistical optimality?'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver