ReHLine: Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence

Ben Dai, Yixuan Qiu
2/12/2026

No official code found. Best implementation: softmin/ReHLine (48 stars, MIT, last commit 2025-12-16).

DOISemantic Scholar

Code Implementations(1)

softmin/ReHLineCommunity72%
MIT

[NeurIPS 2023] Efficient Solver for ERM with PLQ Loss and Linear Constraints

481Oct 5, 202310 months agoMIT
constrained-optimizationconvex-optimizationempirical-risk-minimizationfairness-constrainthuber-loss-regression+8 more

Similar Papers

RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution

100% match1 repo452026

Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset Constraint

99% match1 repo142026

Clean and Compact: Efficient Data-Free Backdoor Defense with Model Compactness

98% match2026

LinkerNet: Fragment Poses and Linker Co-Design with 3D Equivariant Diffusion

98% match1 repo192026

Semi-Supervised Domain Generalization with Known and Unknown Classes

98% match2026

INViTE: INterpret and Control Vision-Language Models with Text Explanations

97% match2026

Cite this paper

@article{dai2026rehline,
  title  = {ReHLine: Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence},
  author = {Ben Dai and Yixuan Qiu},
  year   = {2026},
  doi    = {10.52202/075280-0631},
  url    = {https://doi.org/10.52202/075280-0631},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/398fca2fcf18393c1d73aa542c5243e641473bf6.svg)](https://codeofpaper.com/paper/398fca2fcf18393c1d73aa542c5243e641473bf6)

Discussion