Sparse-penalized deep neural networks estimator under weak dependence

2023/03/02 by William Kengne, Kengne, William, Modou Wade +1 · 1 citation
Computer Science · Engineering · Mathematics · #Distributed Sensor Networks and Detection Algorithms #FOS: Computer and information sciences #FOS: Mathematics #Fault Detection and Control Systems #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistical Methods and Inference #Statistics Theory (math.ST)

paper · pdf · doi:10.48550/arxiv.2303.01406

openalex publication_date 2023/03/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We consider the nonparametric regression and the classification problems for ψ-weakly dependent processes. This weak dependence structure is more general than conditions such as, mixing, association, …. A penalized estimation method for sparse deep neural networks is performed. In both nonparametric regression and binary classification problems, we establish oracle inequalities for the excess risk of the sparse-penalized deep neural networks estimators. Convergence rates of the excess risk of these estimators are also derived. The simulation results displayed show that, the proposed estimators overall work well than the non penalized estimators.

Cited by

• A general framework for deep learning

Related

• Penalized deep neural networks estimator with general loss functions under weak dependence
• Excess risk bound for deep learning under weak dependence
• Nonconvex sparse regularization for deep neural networks and its optimality
• Deep learning from strongly mixing observations: Sparse-penalized regularization and minimax optimality
• Deep learning for ψ-weakly dependent processes