The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Wide neural networks of any depth evolve as linear models under gradient descent *
Open accessAbstract
A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks (NNs) have made a theory of learning dynamics elusive. In this work, we show that for wide NNs the learning dynamics simplify considerably and that, in the infinite width limit, they are governed by a linear model obtained from the first-order Taylor expansion of the network around its initial parameters. Furthermore, mirroring the correspondence between wide Bayesian NNs and Gaussian processes (GPs), gradient-based training of wide NNs with a squared loss produces test set predictions drawn from a GP with a particular compositional kernel. While these theoretical results are only exact in the infinite width limit, we nevertheless find excellent empirical agreement between the predictions of the original network and those of the linearized version even for finite practically-sized networks. This agreement is robust across different architectures, optimization methods, and loss functions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244
On the momentum term in gradient descent learning algorithms
Qian, N. (1999) · Neural Networks · doi:10.1016/s0893-6080(98)00116-6 · Cited by 2,312
Introduction to the non-asymptotic analysis of random matrices
Vershynin, R. (2012) · Compressed Sensing · doi:10.1017/cbo9780511794308.006 · Cited by 2,150
A mean field view of the landscape of two-layer neural networks
Mei, S., Montanari, A., & Nguyen, P.-M. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1806579115 · Cited by 500
Gradient descent optimizes over-parameterized deep ReLU networks
Zou, D., Cao, Y., Zhou, D., & Gu, Q. (2020) · Machine Learning · doi:10.1007/s10994-019-05839-6 · Cited by 227
L2 Regularization versus Batch and Weight Normalization
van Laarhoven, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.05350 · Cited by 188
Cited by
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550
“Expansions in the model size, particularly at large width [JGH18, LXS + 19], may provide a useful framework for thinking about some of our scaling relations.”
BackgroundWhen and why PINNs fail to train: A neural tangent kernel perspective
Wang, S., Yu, X., & Perdikaris, P. (2022) · Journal of Computational Physics · doi:10.1016/j.jcp.2021.110768 · Cited by 1,496
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
Tancik, M., Srinivasan, P. P., Mildenhall, B., Fridovich-Keil, S., Raghavan, N., Singhal, U., Ramamoorthi, R., Barron, J. T., & Ng, R. (2020) · arXiv · doi:10.48550/arxiv.2006.10739 · Cited by 1,459
Wang, S., Wang, H., & Perdikaris, P. (2021) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2021.113938 · Cited by 693
Surprises in high-dimensional ridgeless least squares interpolation
Hastie, T., Montanari, A., Rosset, S., & Tibshirani, R. J. (2022) · The Annals of Statistics · doi:10.1214/21-aos2133 · Cited by 503
Metadata
- Authors
- Lee, J., Xiao, L., Schoenholz, S. S., Bahri, Y., Novak, R., Sohl-Dickstein, J., & Pennington, J.
- Venue
- Journal of Statistical Mechanics: Theory and Experiment
- Publisher
- IOP Publishing
- Published
- 2020-12-01
- Volume
- 2020
- Issue
- 12
- Pages
- 124002
- ISSN
- 1742-5468 (ISSN-L)
- OpenAlex
- W2912322140
- Cited by
- 353
- References
- 8
- FWCI
- 19.13
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Wide neural networks of any depth evolve as linear models under gradient descent *. https://app.cochat.ai/papers/10.1088/1742-5468/abc62b
- The paper
- Lee, J., Xiao, L., Schoenholz, S. S., Bahri, Y., Novak, R., Sohl-Dickstein, J., & Pennington, J. (2020). Wide neural networks of any depth evolve as linear models under gradient descent *. Journal of Statistical Mechanics: Theory and Experiment. https://doi.org/10.1088/1742-5468/abc62b
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.