Saved in:
Bibliographic Details
Main Authors: Luo, Tianpai, Wu, Fangwei, Wu, Weichi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.06265
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914539638882304
author Luo, Tianpai
Wu, Fangwei
Wu, Weichi
author_facet Luo, Tianpai
Wu, Fangwei
Wu, Weichi
contents Quantile regression is a fundamental tool for distributional learning but poses significant optimization challenges for deep models due to the non-smoothness of the pinball loss. We propose ConquerNet, a class of \textbf{con}volution-smoothed \textbf{qu}antil\textbf{e} \textbf{R}eLU neural \textbf{net}works, which yield smooth objectives while preserving the underlying quantile structure. We establish general nonasymptotic risk bounds for ConquerNet under mild conditions, providing minimax guarantees over Besov function classes. In numerical studies, we demonstrate that the proposed approach outperforms standard quantile neural networks at multiple quantile levels, showing improved estimation accuracy and training efficiency across the board, with particularly pronounced advantages at high and low quantiles.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06265
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ConquerNet: Convolution-Smoothed Quantile ReLU Neural Networks with Minimax Guarantees
Luo, Tianpai
Wu, Fangwei
Wu, Weichi
Machine Learning
Quantile regression is a fundamental tool for distributional learning but poses significant optimization challenges for deep models due to the non-smoothness of the pinball loss. We propose ConquerNet, a class of \textbf{con}volution-smoothed \textbf{qu}antil\textbf{e} \textbf{R}eLU neural \textbf{net}works, which yield smooth objectives while preserving the underlying quantile structure. We establish general nonasymptotic risk bounds for ConquerNet under mild conditions, providing minimax guarantees over Besov function classes. In numerical studies, we demonstrate that the proposed approach outperforms standard quantile neural networks at multiple quantile levels, showing improved estimation accuracy and training efficiency across the board, with particularly pronounced advantages at high and low quantiles.
title ConquerNet: Convolution-Smoothed Quantile ReLU Neural Networks with Minimax Guarantees
topic Machine Learning
url https://arxiv.org/abs/2605.06265