On the rate of convergence of a deep recurrent neural network estimate in a regression problem with dependent data-Reference-Cited by-同舟云学术

On the rate of convergence of a deep recurrent neural network estimate in a regression problem with dependent data

Published:2023-05-01 Issue:2 Volume:29 Page:
ISSN:1350-7265
Container-title:Bernoulli
language:
Short-container-title:Bernoulli

Author:

Kohler Michael¹,Krzyżak Adam²

Affiliation:

1. Fachbereich Mathematik, TU Darmstadt, Schlossgartenstr. 7, 64289 Darmstadt, Germany

2. Department of Computer Science and Software Engineering, Concordia University, 1455 De Maisonneuve Blvd. West, Montreal, Quebec, Canada H3G 1M8

Publisher

Bernoulli Society for Mathematical Statistics and Probability

Subject

Statistics and Probability

Reference42 articles.

1. Stone, C.J. (1982). Optimal global rates of convergence for nonparametric regression. Ann. Statist. 10 1040–1053.

2. Bartlett, P.L., Harvey, N., Liaw, C. and Mehrabian, A. (2019). Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks. J. Mach. Learn. Res. 20 Paper No. 63, 17.

3. Bauer, B. and Kohler, M. (2019). On deep learning as a remedy for the curse of dimensionality in nonparametric regression. Ann. Statist. 47 2261–2285. 10.1214/18-AOS1747

4. Bengio, Y., Simard, P. and Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5 157–166.

5. Bruck, J. (1990). On the convergence properties of the Hopfield model. Proc. IEEE 78 1579–1585.

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Deep learning for ψ-weakly dependent processes;Journal of Statistical Planning and Inference;2024-09