Deep double descent: where bigger models and more data hurt

Record

Authors
Nakkiran, P.; Kaplun, G.; Bansal, Y.; Yang, T.; Barak, B.; Sutskever, I.
Year
2020
Title
Deep double descent: where bigger models and more data hurt
Published in
International Conference on Learning Representations
Type
Conference paper
DOI
10.1088/1742-5468/ac3a74
arXiv
arXiv:1912.02292
Links
https://doi.org/10.1088/1742-5468/ac3a74
Our note
none yet
Verification
unverified: not yet checked against the source
Id
nakkiran-2020-deep-double-descent-where-bigger-models

Cited on

As cited

The pages cite this work in 2 forms.

  • Nakkiran, P., Kaplun, G., Bansal, Y., Yang, T., Barak, B., and Sutskever, I. (2020). Deep double descent: where bigger models and more data hurt. International Conference on Learning Representations. arXiv:1912.02292.
  • Nakkiran, P., Kaplun, G., Bansal, Y., Yang, T., Barak, B., and Sutskever, I. (2020). Deep double descent: where bigger models and more data hurt. International Conference on Learning Representations. arXiv:1912.02292; also Journal of Statistical Mechanics: Theory and Experiment (2021), 124003, https://doi.org/10.1088/1742-5468/ac3a74. §§1 and 2; Definition 1 and Hypothesis 1.

BibLaTeX

@inproceedings{nakkiran-2020-deep-double-descent-where-bigger-models,
  author = {Nakkiran, P. and Kaplun, G. and Bansal, Y. and Yang, T. and Barak, B. and Sutskever, I.},
  title = {{Deep double descent: where bigger models and more data hurt}},
  booktitle = {International Conference on Learning Representations},
  date = {2020},
  doi = {10.1088/1742-5468/ac3a74},
  eprint = {1912.02292},
  eprinttype = {arxiv}
}

Download · JSON with CSL-JSON · the whole bibliography