Optimal Approximation with Sparsely Connected Deep Neural Networks
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
We derive fundamental lower bounds on the connectivity and the memory requirements of deep neural networks guaranteeing uniform approximation rates for arbitrary function classes in $L^2(\mathbb{R}^d)$. In other words, we establish a connection between the complexity of a function class and the complexity of deep neural networks approximating functions from this class to within a prescribed accuracy. Additionally, we prove that our lower bounds are achievable for a broad family of function classes. Specifically, all function classes that are optimally approximated by a general class of representation systems---so-called affine systems---can be approximated by deep neural networks with minimal connectivity and memory requirements. Affine systems encompass a wealth of representation systems from applied harmonic analysis such as wavelets, ridgelets, curvelets, shearlets, $\alpha$-shearlets, and, more generally, $\alpha$-molecules. Our central result elucidates a remarkable universality property of neural networks and shows that they achieve the optimum approximation properties of all affine systems combined. As a specific example, we consider the class of $\alpha^{-1}$-cartoon-like functions, which is approximated optimally by $\alpha$-shearlets. We also explain how our results can be extended to the approximation of functions on low-dimensional immersed manifolds. Finally, we present numerical experiments demonstrating that the standard stochastic gradient descent algorithm yields deep neural networks with close-to-optimal approximation rates. Moreover, these results indicate that stochastic gradient descent can learn approximations that are sparse in the representation systems optimally sparsifying the function class the network is trained on.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
A logical calculus of the ideas immanent in nervous activity
McCulloch, W. S., & Pitts, W. (1943) · The Bulletin of Mathematical Biophysics · doi:10.1007/bf02478259 · Cited by 18,566
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
Approximation capabilities of multilayer feedforward networks
Hornik, K. (1991) · Neural Networks · doi:10.1016/0893-6080(91)90009-t · Cited by 6,091
On the approximate realization of continuous mappings by neural networks
Funahashi, K.-I. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90003-8 · Cited by 4,206
Universality of deep convolutional neural networks
Zhou, D.-X. (2020) · Applied and Computational Harmonic Analysis · doi:10.1016/j.acha.2019.06.004 · Cited by 530
Cited by
Machine Learning for Fluid Mechanics
Brunton, S. L., Noack, B. R., & Koumoutsakos, P. (2020) · Annual Review of Fluid Mechanics · doi:10.1146/annurev-fluid-010719-060214 · Cited by 3,063
Solving inverse problems using data-driven models
Arridge, S., Maass, P., Öktem, O., & Schönlieb, C.-B. (2019) · Acta Numerica · doi:10.1017/s0962492919000059 · Cited by 686
Universality of deep convolutional neural networks
Zhou, D.-X. (2020) · Applied and Computational Harmonic Analysis · doi:10.1016/j.acha.2019.06.004 · Cited by 530
Optimal approximation of piecewise smooth functions using deep ReLU neural networks
Petersen, P., & Voigtlaender, F. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.08.019 · Cited by 432
Self-citationTheoretical 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
Metadata
- Authors
- Bölcskei, H., Grohs, P., Kutyniok, G., & Petersen, P.
- Venue
- SIAM Journal on Mathematics of Data Science
- Published
- 2019-01
- Volume
- 1
- Issue
- 1
- Pages
- 8-45
- ISSN
- 2577-0187 (ISSN-L)
- OpenAlex
- W2611375647
- Cited by
- 216
- References
- 10
- FWCI
- 48.94
- Type
- journal article
- Language
- en
- Open access
- diamond
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.