Training neural networks for and by interpolation
In modern supervised learning, many deep neural networks are able to interpolate the data: the empirical loss can be driven to near zero on all samples simultaneously. In this work, we explicitly exploit this interpolation property for the design of a new optimization algorithm for deep learning, wh...
| Hlavní autoři: | , , |
|---|---|
| Médium: | Conference item |
| Jazyk: | English |
| Vydáno: |
Journal of Machine Learning Research
2020
|