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

DOI10.3150/22-BEJ1516OpenAlexW3097022019MaRDI QIDQ2692553

Michael Kohler, Adam Krzyżak

Publication date: 22 March 2023

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.00328

zbMATH Keywords

rate of convergencerecurrent neural networkscurse of dimensionalitynonparametric regression estimation

Mathematics Subject Classification ID

Statistics (62-XX) Artificial intelligence (68Txx) Nonparametric inference (62Gxx)

Uses Software

• LSTM
• astsa
• GloVe

Cites Work

• Optimal global rates of convergence for nonparametric regression
• A distribution-free theory of nonparametric regression
• Estimation of a density using an improved surrogate model
• On the rate of convergence of fully connected deep neural network regression estimates
• Nonparametric regression using deep neural networks with ReLU activation function
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Time Series Analysis and Its Applications
• Deep Network Approximation for Smooth Functions
• Nonparametric Regression Based on Hierarchical Interaction Models
• Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item