Deep double descent: where bigger models and more data hurt

By Preetum Nakkiran, Gal Kaplun, Yamini Bansal, Tristan Yang, Boaz Barak, Ilya Sutskever. 2019

1,162 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Scaling & Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Jianfeng Gao
  3. Percy Liang
  4. Luke S. Zettlemoyer
  5. Yoshua Bengio
  6. Quoc V. Le
  7. Furu Wei
  8. Ruslan Salakhutdinov

In Scaling & Learning Theory

  1. Andrew Gordon Wilson
  2. Hanie Sedghi
  3. Pavel Izmailov
  4. Shotaro Akaho
  5. Ryo Karakida
  6. Neil Houlsby
  7. Matthew D. Hoffman
  8. Behnam Neyshabur

Citations in the corpus