Double descent
Part of a series on |
Machine learning and data mining |
---|
In statistics and machine learning, double descent is the phenomenon where a statistical model with a small number of parameters and a model with an extremely large number of parameters have a small test error, but a model whose number of parameters is about the same as the number of data points used to train the model will have a large error.[2] This phenomenon has been considered surprising, as it contradicts assumptions about overfitting in classical machine learning.[1]
History
[edit]Early observations of what would later be called double descent in specific models date back to 1989.[3][4]
The term "double descent" was coined by Belkin et. al.[5] in 2019,[1] when the phenomenon as a broader concept shared by many models gained popularity.[6][7] The latter development was prompted by a perceived contradiction between the conventional wisdom that too many parameters in the model result in a significant overfitting error (an extrapolation of bias-variance tradeoff),[8] and the empirical observations in the 2010s that some modern machine learning models tend to perform better with larger models.[5][9]
Theoretical models
[edit]Double descent occurs in linear regression with isotropic Gaussian covariates and isotropic Gaussian noise.[10]
A model of double descent at the thermodynamic limit has been analyzed by the replica method, and the result has been confirmed numerically.[11]
Empirical examples
[edit]The scaling behavior of double descent has been found to follow a broken neural scaling law[12] functional form.
References
[edit]- ^ a b c Schaeffer, Rylan; Khona, Mikail; Robertson, Zachary; Boopathy, Akhilan; Pistunova, Kateryna; Rocks, Jason W.; Fiete, Ila Rani; Koyejo, Oluwasanmi (2023-03-24). "Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle". arXiv:2303.14151v1 [cs.LG].
- ^ "Deep Double Descent". OpenAI. 2019-12-05. Retrieved 2022-08-12.
- ^ Vallet, F.; Cailton, J.-G.; Refregier, Ph (June 1989). "Linear and Nonlinear Extension of the Pseudo-Inverse Solution for Learning Boolean Functions". Europhysics Letters. 9 (4): 315. Bibcode:1989EL......9..315V. doi:10.1209/0295-5075/9/4/003. ISSN 0295-5075.
- ^ Loog, Marco; Viering, Tom; Mey, Alexander; Krijthe, Jesse H.; Tax, David M. J. (2020-05-19). "A brief prehistory of double descent". Proceedings of the National Academy of Sciences. 117 (20): 10625–10626. arXiv:2004.04328. Bibcode:2020PNAS..11710625L. doi:10.1073/pnas.2001875117. ISSN 0027-8424. PMC 7245109. PMID 32371495.
- ^ a b Belkin, Mikhail; Hsu, Daniel; Ma, Siyuan; Mandal, Soumik (2019-08-06). "Reconciling modern machine learning practice and the bias-variance trade-off". Proceedings of the National Academy of Sciences. 116 (32): 15849–15854. arXiv:1812.11118. doi:10.1073/pnas.1903070116. ISSN 0027-8424. PMC 6689936. PMID 31341078.
- ^ Spigler, Stefano; Geiger, Mario; d'Ascoli, Stéphane; Sagun, Levent; Biroli, Giulio; Wyart, Matthieu (2019-11-22). "A jamming transition from under- to over-parametrization affects loss landscape and generalization". Journal of Physics A: Mathematical and Theoretical. 52 (47): 474001. arXiv:1810.09665. doi:10.1088/1751-8121/ab4c8b. ISSN 1751-8113.
- ^ Viering, Tom; Loog, Marco (2023-06-01). "The Shape of Learning Curves: A Review". IEEE Transactions on Pattern Analysis and Machine Intelligence. 45 (6): 7799–7819. arXiv:2103.10948. doi:10.1109/TPAMI.2022.3220744. ISSN 0162-8828. PMID 36350870.
- ^ Geman, Stuart; Bienenstock, Élie; Doursat, René (1992). "Neural networks and the bias/variance dilemma" (PDF). Neural Computation. 4: 1–58. doi:10.1162/neco.1992.4.1.1. S2CID 14215320.
- ^ Preetum Nakkiran; Gal Kaplun; Yamini Bansal; Tristan Yang; Boaz Barak; Ilya Sutskever (29 December 2021). "Deep double descent: where bigger models and more data hurt". Journal of Statistical Mechanics: Theory and Experiment. 2021 (12). IOP Publishing Ltd and SISSA Medialab srl: 124003. arXiv:1912.02292. Bibcode:2021JSMTE2021l4003N. doi:10.1088/1742-5468/ac3a74. S2CID 207808916.
- ^ Nakkiran, Preetum (2019-12-16). "More Data Can Hurt for Linear Regression: Sample-wise Double Descent". arXiv:1912.07242v1 [stat.ML].
- ^ Advani, Madhu S.; Saxe, Andrew M.; Sompolinsky, Haim (2020-12-01). "High-dimensional dynamics of generalization error in neural networks". Neural Networks. 132: 428–446. doi:10.1016/j.neunet.2020.08.022. ISSN 0893-6080. PMC 7685244. PMID 33022471.
- ^ Caballero, Ethan; Gupta, Kshitij; Rish, Irina; Krueger, David (2022). "Broken Neural Scaling Laws". International Conference on Learning Representations (ICLR), 2023.
Further reading
[edit]- Mikhail Belkin; Daniel Hsu; Ji Xu (2020). "Two Models of Double Descent for Weak Features". SIAM Journal on Mathematics of Data Science. 2 (4): 1167–1180. arXiv:1903.07571. doi:10.1137/20M1336072.
- Mount, John (3 April 2024). "The m = n Machine Learning Anomaly".
- Preetum Nakkiran; Gal Kaplun; Yamini Bansal; Tristan Yang; Boaz Barak; Ilya Sutskever (29 December 2021). "Deep double descent: where bigger models and more data hurt". Journal of Statistical Mechanics: Theory and Experiment. 2021 (12). IOP Publishing Ltd and SISSA Medialab srl: 124003. arXiv:1912.02292. Bibcode:2021JSMTE2021l4003N. doi:10.1088/1742-5468/ac3a74. S2CID 207808916.
- Song Mei; Andrea Montanari (April 2022). "The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve". Communications on Pure and Applied Mathematics. 75 (4): 667–766. arXiv:1908.05355. doi:10.1002/cpa.22008. S2CID 199668852.
- Xiangyu Chang; Yingcong Li; Samet Oymak; Christos Thrampoulidis (2021). "Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks". Proceedings of the AAAI Conference on Artificial Intelligence. 35 (8). arXiv:2012.08749.
External links
[edit]- Brent Werness; Jared Wilber. "Double Descent: Part 1: A Visual Introduction".
- Brent Werness; Jared Wilber. "Double Descent: Part 2: A Mathematical Explanation".
- Understanding "Deep Double Descent" at evhub.