Research map / Learning theory and algorithms / Matrix and tensor methods
ReHLine: Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence
Ben Dai, Yixuan Qiu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use ReHLine instead of generic ECOS | FairSVM · Creditcard | running time: 273x | Improved |
| use ReHLine instead of MOSEK | FairSVM · Creditcard | running time: 100x | Improved |
| use ReHLine instead of SCS | FairSVM · Creditcard | running time: 252x | Improved |
| use ReHLine instead of the original DCCP solver | FairSVM · Creditcard | running time | Improved |
| use ReHLine instead of ECOS | ElasticQR · BT | running time: 2843x | Improved |
| use ReHLine instead of MOSEK/SCS | ElasticQR · BT | running time | Improved |
| use ReHLine instead of MOSEK | RidgeHuber · BT | running time: 452x | Improved |
| use ReHLine instead of specialized HQREG | RidgeHuber · BT | running time: 2.37x | Improved |
| use ReHLine instead of HQREG on small data | RidgeHuber · Kin8nm | running time: 1.58 -> 2.04 | Hurt |
| use ReHLine instead of ECOS | SVM · Creditcard | running time: 415x | Improved |
| use ReHLine instead of SCS | SVM · Creditcard | running time: 340x | Improved |
| use ReHLine instead of specialized LIBLINEAR | SVM · Creditcard | running time: 4.5x | Improved |
Later papers that compared with this method
1 later accepted paper reports ReHline as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Finite Smoothing Algorithm for High-Dimensional Support Vector Machines and Quantile Regression (ICML 2024 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Solving L1-regularized SVMs and Related Linear Programs: Revisiting the Effectiveness of Column and Constraint Generation (JMLR 2022 · similarity 0.85)
- Robust high dimensional learning for Lipschitz and convex losses (JMLR 2020 · similarity 0.85)
- The Common-directions Method for Regularized Empirical Risk Minimization (JMLR 2019 · similarity 0.84)
- Tight Lower Bounds and Improved Convergence in Performative Prediction (NeurIPS 2025 · similarity 0.84)
- A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization (TPAMI 2021 · similarity 0.84)
- Doubly Accelerated Stochastic Variance Reduced Dual Averaging Method for Regularized Empirical Risk Minimization (NeurIPS 2017 · similarity 0.84)
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.
