Research map / Learning theory and algorithms / Kernels and regression theory
Multi-Class Learning: From Theory to Algorithm
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 |
|---|---|---|---|
| add local Rademacher regularization (SMSD-MKL) to mixed-norm MKL (UFO-MKL) | MC-MKL · plant | accuracy: 76.77±2.42 -> 78.01±2.17 | Helped |
| add local Rademacher regularization (SMSD-MKL) to mixed-norm MKL (UFO-MKL) | MC-MKL · psortPos | accuracy: 74.56±4.04 -> 76.23±3.39 | Helped |
| add local Rademacher regularization (SMSD-MKL) to mixed-norm MKL (UFO-MKL) | MC-MKL · satimage | accuracy: 91.92±0.83 -> 91.78±0.82 | No clear effect |
| add local Rademacher regularization (SMSD-MKL) to mixed-norm MKL (UFO-MKL) | MC-MKL · vehicle | accuracy: 76.92±2.83 -> 77.28±2.78 | Mixed |
| use SMSD-MKL instead of Conv-MKL | local Rademacher MKL · 14 benchmark datasets | accuracy: wins on 2/3 datasets | Helped |
| use multiple kernels (MKL) instead of single kernel methods | multi-class SVM · 14 benchmark datasets | accuracy | Helped |
| use kernel methods instead of linear LMC | multi-class classifier · 14 benchmark datasets | accuracy: e.g. 62.32±4.97 -> 98.82±1.19 on vowel | Helped |
Closest papers by meaning
- Infinite Kernel Learning: Generalization Bounds and Algorithms (AAAI 2017 · similarity 0.88)
- The optimality of kernel classifiers in Sobolev space (ICLR 2024 · similarity 0.86)
- Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals (NeurIPS 2026 · similarity 0.85)
- Multi-View Randomized Kernel Classification via Nonconvex Optimization (AAAI 2024 · similarity 0.85)
- Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel (NeurIPS 2025 · similarity 0.84)
- Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification (NeurIPS 2025 · 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.