AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Non-splitting Neyman-Pearson Classifiers

Jingming Wang, Lucy Xia, Zhigang Bao, Xin Tong

JMLR 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data

Read the paper

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 all training data (non-splitting) for both scoring and threshold instead of sample splittingeLDA vs pNP-LDA · Toy LDA example (n0=n1=50)type II error: .7638 -> .4478Improved
Use non-splitting eLDA instead of pNP-LDAlung cancer dataset · Lung cancer dataset (alpha=0.01, delta=0.05)type II error: 1 -> .104Improved
Use non-splitting eLDA instead of pNP-LDAmulti-tumor cancer dataset · Cancer dataset (n0=83, n1=91)type II error: 1 -> .437Improved
Use eLDA instead of splitting NP methods on observed violation rateeLDA · Simulation Example 1atype I error violation rate: pNP-LDA largest 0.007 vs eLDA around delta=0.1Improved
Use the fixed-dimension variant feLDA instead of eLDA as p grows to 20 and beyondfeLDA · Simulation Example 1ctype I error controlHurt
Lower the violation target delta from 0.1 to 0.05 and 0.01 for feLDA (ablation)feLDA · Simulation Example 1c, 1c', 1c*type I error as p increasesNo clear effect
Lower delta from 0.1 to 0.05 for NP umbrella algorithm classifiers (ablation)NP-LDA, NP-sLDA, NP-penlog, NP-svm · Simulation Example 1c vs 1c'observed violation rate: k* = 61 for both delta=0.1 and delta=0.05No clear effect
Lower delta to 0.01 for NP umbrella algorithm classifiers (ablation)NP umbrella methods · Simulation Example 1c*observed violation rate: nu(61)=0.042 > 0.01 so threshold changesImproved
Use eLDA over splitting methods at large n0 under heavy-tailed non-Gaussian dataeLDA/feLDA · Non-Gaussian simulationstype II errorMixed
Increase dimension p for pNP-LDA (ablation)pNP-LDA · Simulation Example 1ctype II errorHurt
Fix n1=500 and vary n0 (Example 1b) instead of balanced sizes (ablation)pNP-LDA · Simulation Example 1a vs 1blargest violation rate: 0.007 -> 0.028Mixed

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