Research map / Learning theory and algorithms / Prediction and decision losses
Binary Classification with Karmic, Threshold-Quasi-Concave Metrics
Bowei Yan, Sanmi Koyejo, Kai Zhong, Pradeep Ravikumar
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 a two-step plug-in classifier that estimates the conditional probability and threshold separately | Binary classification with Karmic, threshold-quasi-concave metrics · General Karmic metrics | excess utility: c_5 \max\left\{ a_n^{-\frac{1+\alpha}{2}},b_n^{-1} \right\} | Improved |
| Estimate the threshold using binary search on the thresholded utility gradient | Two-step plug-in classifier · General Karmic metrics | excess utility: c_{9} \max\left\{ \frac{\log n}{n},\frac{\log a_n}{a_n},a_{n}^{-\frac{1+\alpha}{2}} \right\} | Improved |
| Apply the plug-in classifier with logistic-regression MLE to the Gaussian generative model | Two-step plug-in classifier · Gaussian generative model | excess utility: O\left( \frac{\log n}{n} \right) | Improved |
| Use a locally polynomial or kernel conditional-density estimator for β-Hölder conditional probabilities | Two-step plug-in classifier · β-Hölder conditional probability | excess utility: O\left( n^{-\frac{(\min\{\alpha,1\}+1)\beta}{2\beta+d}} \right) | Improved |
Closest papers by meaning
- Optimal Binary Classification Beyond Accuracy (NeurIPS 2022 · similarity 0.89)
- Post-Processing Guarantees for Classification under Linear-Fractional Performance Metrics (NeurIPS 2026 · similarity 0.88)
- Consistency Analysis for Binary Classification Revisited (ICML 2017 · similarity 0.88)
- Principled Algorithms for Optimizing Generalized Metrics in Binary Classification (ICML 2025 · similarity 0.87)
- A General Online Algorithm for Optimizing Complex Performance Metrics (ICML 2024 · similarity 0.85)
- Leveraging Uncertainty Estimates To Improve Classifier Performance (ICLR 2024 · 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.
