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

A regression problem with dependent data is considered. Regularity assumptions on the dependency of the data are introduced, and it is shown that under suitable structural assumptions on the regression function a deep recurrent neural network estimate is able to circumvent the curse of dimensionality.

stat.ML cs.LG Computer Science Mathematics

Paper

References (35)

01On the rate of convergence of fully connected deep neural network regression estimatesMichael Kohler, S. Langer2021 · Annals of Statistics · 182 citations

02Prediction of Hilbertian autoregressive processes : a Recurrent Neural Network approachClément Carré, André Mas2020 · arXiv.org · 2 citations In Library

03Deep Network Approximation for Smooth FunctionsJianfeng Lu, Zuowei Shen, Haizhao Yang et al.2020 · SIAM Journal on Mathematical Analysis · 315 citations In Library

04A hybrid method of exponential smoothing and recurrent neural networks for time series forecastingSlawek Smyl2020 · International Journal of Forecasting · 770 citations

05Recurrent Neural Networks for Time Series Forecasting: Current Status and Future DirectionsHansika Hewamalage, C. Bergmeir, Kasun Bandara2019 · International Journal of Forecasting · 1.3k citations In Library

06The phase diagram of approximation rates for deep neural networksD. Yarotsky, Anton Zhevnerchuk2019 · Neural Information Processing Systems · 153 citations In Library

07On deep learning as a remedy for the curse of dimensionality in nonparametric regressionB. Bauer, M. Kohler2019 · Annals of Statistics · 316 citations

08Statistical and Machine Learning forecasting methods: Concerns and ways forwardS. Makridakis, Evangelos Spiliotis, V. Assimakopoulos2018 · PLoS ONE · 1.4k citations

09Optimal approximation of continuous functions by very deep ReLU networksD. Yarotsky2018 · Annual Conference Computational Learning Theory · 340 citations In Library

10Recent Advances in Recurrent Neural NetworksH. Salehinejad, J. Baarbé, Sharan Sankar et al.2017 · arXiv.org · 745 citations In Library

11Deep Convolutional Neural Networks for Image Classification: A Comprehensive ReviewWaseem Rawat, Zenghui Wang2017 · Neural Computation · 3.2k citations

12Nonparametric regression using deep neural networks with ReLU activation functionJ. Schmidt-Hieber2017 · Annals of Statistics · 1.1k citations In Library

Scroll for more · 23 remaining

Similar papers

On the rate of convergence of a deep recurrent neural network estimate in a regression problem with dependent dataMichael Köhler, Adam Krzyżak2023 · Bernoulli In Library

On the rate of convergence of fully connected very deep neural network regression estimatesM. Kohler, S. Langer2019 · arXiv.org · 40 citations In Library

Statistical Properties of Deep Neural Networks with Dependent DataChad E. Brown2024 · arXiv (Cornell University) · 4 citations In Library

Analysis of the Rate of Convergence of an Over-Parametrized Deep Neural Network Estimate Learned by Gradient DescentMichael Köhler, Adam Krzyżak2025 · IEEE Transactions on Information Theory In Library

Analysis of the rate of convergence of neural network regression estimates which are easy to implement.Alina Braun, M. Kohler, A. Krzyżak2019 · arXiv: Statistics Theory · 1 citation In Library

Analysis of the Rate of Convergence of an Over-Parametrized Deep Neural Network Estimate Learned by Gradient DescentM. Kohler, A. Krzyżak2022 · IEEE Transactions on Information Theory · 12 citations In Library

Analysis of the rate of convergence of fully connected deep neural\n network regression estimates with smooth activation functionSophie Langer2020 · arXiv (Cornell University) · 23 citations In Library

Analysis of the rate of convergence of two regression estimates defined by neural features which are easy to implementAlina Braun, Michael Köhler, Jeongik Cho et al.2024 · Electronic Journal of Statistics In Library

Deep Regression for Repeated MeasurementsShunxing Yan, Fang Yao, Hang Zhou2025 · Journal of the American Statistical Association In Library

Theoretical analysis of deep neural networks for temporally dependent observationsMingliang Ma, Abolfazl Safikhani2022 · Neural Information Processing Systems · 20 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal