Deep Double Descent: Where Bigger Models and More Data Hurt
Abstract
We show that a variety of modern deep learning tasks exhibit a "double-descent" phenomenon where, as we increase model size, performance first gets worse and then gets better. Moreover, we show that double descent occurs not just as a function of model size, but also as a function of the number of training epochs. We unify the above phenomena by defining a new complexity measure we call the effective model complexity, and conjecture a generalized double descent with respect to this measure. Furthermore, our notion of model complexity allows us to identify certain regimes where increasing (even quadrupling) the number of train samples actually hurts test performance.
Cite
Text
Nakkiran et al. "Deep Double Descent: Where Bigger Models and More Data Hurt." International Conference on Learning Representations, 2020.Markdown
[Nakkiran et al. "Deep Double Descent: Where Bigger Models and More Data Hurt." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/nakkiran2020iclr-deep/)BibTeX
@inproceedings{nakkiran2020iclr-deep,
title = {{Deep Double Descent: Where Bigger Models and More Data Hurt}},
author = {Nakkiran, Preetum and Kaplun, Gal and Bansal, Yamini and Yang, Tristan and Barak, Boaz and Sutskever, Ilya},
booktitle = {International Conference on Learning Representations},
year = {2020},
url = {https://mlanthology.org/iclr/2020/nakkiran2020iclr-deep/}
}