NeurIPS 2019poster1127 citations
On Lazy Training in Differentiable Programming
Lénaïc Chizat, Edouard Oyallon, Francis Bach
Abstract
In a series of recent theoretical works, it was shown that strongly over-parameterized neural networks trained with gradient-based methods could converge exponentially fast to zero training loss, with their parameters hardly varying. In this work, we show that this
BibTeX
@inproceedings{NEURIPS2019_ae614c55,
author = {Chizat, L\'{e}na\"{\i}c and Oyallon, Edouard and Bach, Francis},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {On Lazy Training in Differentiable Programming},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/ae614c557843b1df326cb29c57225459-Paper.pdf},
volume = {32},
year = {2019}
}