The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
A mean field view of the landscape of two-layer neural networks
Open accessAbstract
Significance: Multilayer neural networks have proven extremely successful in a variety of tasks, from image classification to robotics. However, the reasons for this practical success and its precise domain of applicability are unknown. Learning a neural network from data requires solving a complex optimization problem with millions of variables. This is done by stochastic gradient descent (SGD) algorithms. We study the case of two-layer networks and derive a compact description of the SGD dynamics in terms of a limiting partial differential equation. Among other consequences, this shows that SGD dynamics does not become more complex when the network size increases.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Advances in Neural Information Processing Systems 19
(2007) · The MIT Press eBooks · doi:10.52202/085713 · Cited by 15,539
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
(2016) · Cited by 11,679
A Stochastic Approximation Method
Robbins, H., & Monro, S. (1951) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177729586 · Cited by 9,643
Linear and Quasi-linear Equations of Parabolic Type
Ladyženskaja, O., Solonnikov, V., & Ural′ceva, N. (1968) · Translations of Mathematical Monographs · doi:10.1090/mmono/023 · Cited by 7,490
Large-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2010) · Proceedings of COMPSTAT'2010 · doi:10.1007/978-3-7908-2604-3_16 · Cited by 5,795
Partial Differential Equations
Evans, L. (2010) · Graduate Studies in Mathematics · doi:10.1090/gsm/019 · Cited by 3,648
Understanding Machine Learning: From Theory to Algorithms
Shalev-Shwartz, S., & Ben-David, S. (2014) · doi:10.1017/cbo9781107298019 · Cited by 3,115
(2015) · Cited by 2,857
(2008) · doi:10.1007/978-3-7643-8722-8 · Cited by 2,220
Mullin, A. A., & Rosenblatt, F. (1963) · The American Mathematical Monthly · doi:10.2307/2312103 · Cited by 2,209
The Variational Formulation of the Fokker--Planck Equation
Jordan, R., Kinderlehrer, D., & Otto, F. (1998) · SIAM Journal on Mathematical Analysis · doi:10.1137/s0036141096303359 · Cited by 1,603
Topics in propagation of chaos
Sznitman, A. (1991) · Lecture notes in mathematics · doi:10.1007/bfb0085169 · Cited by 1,358
Bartlett, P. L. (1998) · IEEE Transactions on Information Theory · doi:10.1109/18.661502 · Cited by 1,166
ImageNet classification with deep convolutional neural networks
Krizhevsky (2012) · Medical Entomology and Zoology · Cited by 799
Guillemin, V., & Pollack, A. (2010) · American Mathematical Society eBooks · doi:10.1090/chel/370 · Cited by 654
Carrillo, J. A., McCann, R. J., & Villani, C. (2003) · Revista Matemática Iberoamericana · doi:10.4171/rmi/376 · Cited by 477
Large-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2011) · Chapman & Hall/CRC Computer Science & Data Analysis · doi:10.1201/b11429-4 · Cited by 460
Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks
Soltanolkotabi, M., Javanmard, A., & Lee, J. D. (2019) · IEEE Transactions on Information Theory · doi:10.1109/tit.2018.2854560 · Cited by 356
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal TransportPreprint
Chizat, L., & Bach, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09545 · Cited by 334
Recovery Guarantees for One-hidden-layer Neural NetworksPreprint
Zhong, K., Song, Z., Jain, P., Bartlett, P. L., & Dhillon, I. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.03175 · Cited by 311
A Stochastic Approximation Method
Robbins, H., & Monro, S. (1985) · Herbert Robbins Selected Papers · doi:10.1007/978-1-4612-5110-1_9 · Cited by 284
Global-in-time weak measure solutions and finite-time aggregation for nonlocal interaction equations
Carrillo, J. A., DiFrancesco, M., Figalli, A., Laurent, T., & Slepčev, D. (2011) · Duke Mathematical Journal · doi:10.1215/00127094-2010-211 · Cited by 279
Gradient Flows of Probability Measures
Ambrosio, L., & Savaré, G. (2007) · Handbook of differential equations. Evolutionary equations · doi:10.1016/s1874-5717(07)80004-1 · Cited by 259
Provable Bounds for Learning Some Deep Representations
Arora, S., Bhaskara, A., Ge, R., & Ma, T. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1310.6343 · Cited by 240
The landscape of empirical risk for nonconvex losses
Mei, S., Bai, Y., & Montanari, A. (2018) · The Annals of Statistics · doi:10.1214/17-aos1637 · Cited by 216
Self-citationLearning One-hidden-layer Neural Networks with Landscape DesignPreprint
Ge, R., Lee, J. D., & Ma, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.00501 · Cited by 210
Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor MethodsPreprint
Janzamin, M., Sedghi, H., & Anandkumar, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.08473 · Cited by 176
Bengio, Y., Roux, N. L., Vincent, P., Delalleau, O., & Marcotte, P. (2005) · Cited by 153
Efficient agnostic learning of neural networks with bounded fan-in
Lee, W. S., Bartlett, P. L., & Williamson, R. C. (1996) · IEEE Transactions on Information Theory · doi:10.1109/18.556601 · Cited by 150
Markowich, P. A., & Villani, C. (2004) · Cited by 144
Rotskoff, G. M., & Vanden‐Eijnden, E. (2018) · arXiv (Cornell University) · Cited by 100
l 1 -regularized neural networks are improperly learnable in polynomial time
Zhang, Y., Lee, J. D., & Jordan, M. I. (2016) · Cited by 90
Provable Methods for Training Neural Networks with Sparse ConnectivityPreprint
Sedghi, H., & Anandkumar, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.2693 · Cited by 57
Wang, C., Mattingly, J. C., & Lu, Y. M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.04332 · Cited by 32
Symmetry-Breaking Convergence Analysis of Certain Two-layered Neural Networks with ReLU nonlinearity
Tian, Y. (2017) · International Conference on Learning Representations · Cited by 26
Cited by
Physics-informed machine learning
Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021) · Nature Reviews Physics · doi:10.1038/s42254-021-00314-5 · Cited by 8,718
Introduction to Machine Learning, Neural Networks, and Deep Learning.
Choi, R. Y., Coyner, A. S., Kalpathy–Cramer, J., Chiang, M. F., & Campbell, J. P. (2020) · PubMed · doi:10.1167/tvst.9.2.14 · Cited by 1,012
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-citationEmpirical Asset Pricing via Machine Learning
Gu, S., Kelly, B., & Xiu, D. (2018) · National Bureau of Economic Research · doi:10.3386/w25398 · Cited by 378
Metadata
- Authors
- Mei, S., Montanari, A., & Nguyen, P.-M.
- Venue
- Proceedings of the National Academy of Sciences
- Published
- 2018-07-27
- Volume
- 115
- Issue
- 33
- Pages
- E7665-E7671
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- OpenAlex
- W2963095610
- Cited by
- 500
- References
- 37
- FWCI
- 33.24
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
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.