Research map / Label-efficient and robust learning / Recognition and long-tail
Angle-based Multicategory Distance-weighted SVM
Hui Sun, Bruce A. Craig, Lingsong Zhang
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 MDWSVM instead of MSVM and MDWD | MDWSVM · Phone calls (Monday, Friday) | prediction error: Monday 0.6200 -> 0.4111; Friday 0.5527 -> 0.3200 | Improved |
| use MDWSVM instead of MSVM | MDWSVM · Phone calls | total error rate: 0.2702 -> 0.2053 | Improved |
| use MDWSVM instead of MSVM | MDWSVM · Phone calls | average within-group error rate: 0.4107 -> 0.2765 | Improved |
| use MDWSVM instead of MDWD | MDWSVM · Phone calls (Tue-Thu) | prediction error: 0.0396 -> 0.0985 | Hurt |
| use MDWSVM instead of MSVM and MDWD under imbalanced classes | MDWSVM · simulation Examples 1-3 | prediction error and angle to Bayes rule | Improved |
| use MDWSVM instead of MSVM and MDWD under balanced classes | MDWSVM · simulation Examples 1-3 | prediction error and angle to Bayes rule | No clear effect |
| increase dimension from 2 to 1000 | MDWSVM · MDWSVM, MSVM, MDWD | prediction error | Hurt |
| vary alpha from 0.1 to 0.9 (ablation) | MDWSVM · MDWSVM | Example 1 prediction error | No clear effect |
| increase C from 2^-3 up to 2^12 (ablation) | MDWSVM · MDWSVM | Example 1 prediction error | Mixed |
| combine SVM and DWD losses (MDWSVM) instead of MSVM | MDWSVM · MSVM | computation time (s), dimension 1000: 9.30 -> 41.66 | Hurt |
| use MDWSVM instead of MDWD | MDWSVM · MDWD | computation time (s), dimension 1000: 27.43 -> 41.66 | Hurt |
Closest papers by meaning
- Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory (ICML 2018 · similarity 0.86)
- A Unified View on Multi-class Support Vector Classification (JMLR 2016 · similarity 0.84)
- Handling Multi-Class Problem by Intuitionistic Fuzzy Twin Support Vector Machines Based on Relative Density Information (TPAMI 2023 · similarity 0.83)
- Unified Locally Linear Classifiers With Diversity-Promoting Anchor Points (AAAI 2018 · similarity 0.82)
- Multi-Class Support Vector Machine with Maximizing Minimum Margin (AAAI 2024 · similarity 0.82)
- GenSVM: A Generalized Multiclass Support Vector Machine (JMLR 2016 · similarity 0.81)
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.
