Research map / Learning theory and algorithms / Kernels and regression theory
Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
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 least squares instead of class averaging when classes have different mean norms and sample size is large | Linear multiclass classifier on GMM (k=9, d=300) · GMM synthetic, different mean norms | test misclassification error | Helped |
| use class averaging instead of least squares with equal priors and equal-norm means | Linear multiclass classifier on GMM · GMM synthetic, scenario (a) | test misclassification error | Helped |
| use weighted least squares instead of unweighted LS | Least-squares classifier on GMM with unequal priors · GMM class-wise error | class-wise test error flatness | Helped |
| use cross-entropy instead of LS/averaging | Linear classifier on MLM (k=9 orthogonal classes) · MLM synthetic | test misclassification error | Helped |
| use LS instead of CE with large sample size | Linear classifier on GMM · GMM synthetic | test misclassification error | Helped |
Closest papers by meaning
- Precise asymptotic generalization for multiclass classification with overparameterized linear models (NeurIPS 2023 · similarity 0.90)
- Generalization for multiclass classification with overparameterized linear models (NeurIPS 2022 · similarity 0.90)
- Demystifying the Optimal Performance of Multi-Class Classification (NeurIPS 2023 · similarity 0.89)
- Multiclass Classification with Rare Useful Features: Fundamental Limits and the Optimality of Diversity Pursuit Higher Criticism (NeurIPS 2026 · similarity 0.89)
- Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals (NeurIPS 2026 · similarity 0.87)
- The Implicit Bias of Gradient Descent on Separable Multiclass Data (NeurIPS 2024 · similarity 0.86)
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.