AI Paper Atlas

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

ICML 2018 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking-based loss optimization · 10 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use a two-step plug-in classifier that estimates the conditional probability and threshold separatelyBinary classification with Karmic, threshold-quasi-concave metrics · General Karmic metricsexcess 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 gradientTwo-step plug-in classifier · General Karmic metricsexcess 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 modelTwo-step plug-in classifier · Gaussian generative modelexcess utility: O\left( \frac{\log n}{n} \right)Improved
Use a locally polynomial or kernel conditional-density estimator for β-Hölder conditional probabilitiesTwo-step plug-in classifier · β-Hölder conditional probabilityexcess utility: O\left( n^{-\frac{(\min\{\alpha,1\}+1)\beta}{2\beta+d}} \right)Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy