Research map / Learning theory and algorithms / Sample complexity
Nonparametric Quantile Regression with ReLU-Activated Recurrent Neural Networks
Hang Yu, Lyumin Wu, Wenxin Zhou, Zhao Ren
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies nonparametric quantile regression with ReLU recurrent neural networks and sparse RNNs, showing near-optimal estimation rates under a compositional hierarchical interaction model.
Problem
Estimating the conditional quantile function nonparametrically when it follows a compositional hierarchical interaction model, using recurrent architectures.
Approach
Shows that RNN and sparse RNN estimators with ReLU activation and appropriately designed architectures attain the optimal nonparametric convergence rate for quantile regression under compositional hierarchical structure.
Key results
- RNN- and SRNN-based quantile estimators with ReLU activation and appropriately designed architectures achieve the optimal nonparametric convergence rate (per the abstract, truncated).
Closest papers by meaning
- Nonparametric Estimation of Non-Crossing Quantile Regression Process with Deep ReQU Neural Networks (JMLR 2024 · similarity 0.91)
- Quantile regression with ReLU Networks: Estimators and minimax rates (JMLR 2022 · similarity 0.90)
- Deep Nonparametric Quantile Regression under Covariate Shift (JMLR 2024 · similarity 0.89)
- Simulation-Based Inference with Quantile Regression (ICML 2024 · similarity 0.86)
- Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate (ICML 2025 · similarity 0.83)
- Nonparametric Instrumental Variable Regression through Stochastic Approximate Gradients (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
