Research map / Learning theory and algorithms / Prediction and decision losses
Minimax Classification with 0-1 Loss and Performance Guarantees
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 MRC instead of SVM | MRC · Mammog. | classification error: $.18\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.03$ -> $.18\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.04$ | No clear effect |
| Use MRC instead of SVM | MRC · Haberman | classification error: $.26\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.04$ -> $.27\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.03$ | Hurt |
| Use MRC instead of SVM | MRC · Indian liv. | classification error: $.29\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.02$ -> $.29\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.01$ | No clear effect |
| Use MRC instead of SVM | MRC · Diabetes | classification error: $.24\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.04$ -> $.26\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.03$ | Hurt |
| Use MRC instead of KNN | MRC · Credit | classification error: $.14\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.09$ -> $.15\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.18$ | Mixed |
| Use MRC instead of KNN | MRC · Glass | classification error: $.34\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.08$ -> $.36\,$\raisebox{1.5pt}{$\mathsmaller{\pm}$}$\,.08$ | Hurt |
Closest papers by meaning
- A Minimax Approach to Supervised Learning (NeurIPS 2016 · similarity 0.87)
- Regret Bounds for Multilabel Classification in Sparse Label Regimes (NeurIPS 2022 · similarity 0.87)
- Robust Minimax Boosting with Performance Guarantees (NeurIPS 2025 · similarity 0.86)
- Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification (NeurIPS 2025 · similarity 0.85)
- A Universal Growth Rate for Learning with Smooth Surrogate Losses (NeurIPS 2024 · similarity 0.85)
- Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification (NeurIPS 2026 · similarity 0.85)
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.