Linearized two-layers neural networks in high dimension
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
We consider the problem of learning an unknown function f⋆ on the d-dimensional sphere with respect to the square loss, given i.i.d. samples {(yi,xi)}i≤n where xi is a feature vector uniformly distributed on the sphere and yi=f⋆(xi)+εi. We study two popular classes of models that can be regarded as linearizations of two-layers neural networks around a random initialization: the random features model of Rahimi–Recht (RF); the neural tangent model of Jacot–Gabriel–Hongler (NT). Both these models can also be regarded as randomized approximations of kernel ridge regression (with respect to different kernels), and enjoy universal approximation properties when the number of neurons N diverges, for a fixed dimension d. We consider two specific regimes: the infinite-sample finite-width regime, in which n=∞ while d and N are large but finite, and the infinite-width finite-sample regime in which N=∞ while d and n are large but finite. In the first regime, we prove that if dℓ+δ≤N≤dℓ+1−δ for small δ>0, then RF effectively fits a degree-ℓ polynomial in the raw features, and NT fits a degree-(ℓ+1) polynomial. In the second regime, both RF and NT reduce to kernel methods with rotationally invariant kernels. We prove that, if the sample size satisfies dℓ+δ≤n≤dℓ+1−δ, then kernel methods can fit at most a degree-ℓ polynomial in the raw features. This lower bound is achieved by kernel ridge regression, and near-optimal prediction error is achieved for vanishing ridge regularization.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883
An Introduction to Support Vector Machines and Other Kernel-based Learning Methods
Cristianini, N., & Shawe-Taylor, J. (2000) · doi:10.1017/cbo9780511801389 · Cited by 13,855
Approximation capabilities of multilayer feedforward networks
Hornik, K. (1991) · Neural Networks · doi:10.1016/0893-6080(91)90009-t · Cited by 6,091
Reconciling modern machine-learning practice and the classical bias–variance trade-off
Belkin, M., Hsu, D., Ma, S., & Mandal, S. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1903070116 · Cited by 1,595
Neural Tangent Kernel: Convergence and Generalization in Neural Networks
Jacot, A., Gabriel, F., & Hongler, C. (2018) · arXiv · doi:10.48550/arxiv.1806.07572 · Cited by 1,562
The generalization error of random features regression: Precise asymptotics and double descent curve
Mei, S., & Montanari, A. (2019) · arXiv · doi:10.48550/arxiv.1908.05355 · Cited by 537
Self-citation
Cited by
The generalization error of random features regression: Precise asymptotics and double descent curve
Mei, S., & Montanari, A. (2019) · arXiv · doi:10.48550/arxiv.1908.05355 · Cited by 537
Self-citationSurprises 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
Self-citationTowards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
Allen-Zhu, Z., & Li, Y. (2020) · arXiv · doi:10.48550/arxiv.2012.09816 · Cited by 178
On the linearity of large non-linear models: when and why the tangent kernel is constant
Liu, C., Zhu, L., & Belkin, M. (2020) · arXiv · doi:10.48550/arxiv.2010.01092 · Cited by 51
Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian
Oymak, S., Fabian, Z., Li, M., & Soltanolkotabi, M. (2019) · arXiv · doi:10.48550/arxiv.1906.05392 · Cited by 44
Metadata
- Authors
- Ghorbani, B., Mei, S., Misiakiewicz, T., & Montanari, A.
- Venue
- The Annals of Statistics
- Publisher
- Institute of Mathematical Statistics
- Published
- 2021-04-01
- Volume
- 49
- Issue
- 2
- Pages
- 1029-1054
- ISSN
- 0090-5364 (ISSN-L)
- OpenAlex
- W2941057241
- Cited by
- 142
- References
- 6
- FWCI
- 6.26
- 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: Linearized two-layers neural networks in high dimension. https://app.cochat.ai/papers/10.1214/20-aos1990
- The paper
- Ghorbani, B., Mei, S., Misiakiewicz, T., & Montanari, A. (2021). Linearized two-layers neural networks in high dimension. The Annals of Statistics. https://doi.org/10.1214/20-aos1990
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.