AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Optimizing ROC Curves with a Sort-Based Surrogate Loss for Binary Classification and Changepoint Detection

Jonathan Hillman, Toby Dylan Hocking

JMLR 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking-based loss optimization

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 AUM with FP/FN counts instead of rates (ablation)AUM linear model · zip 0/1, 50% positive trainmedian test AUC: 0.9979 -> 0.9993Improved
Use AUM with FP/FN counts instead of rates (ablation)AUM linear model · zip 0/1, 1% positive trainmedian test AUC: 0.9928 -> 0.9979Improved
Train with AUM instead of weighted logistic losslinear model · zip 0/1, 1% positive trainmedian test AUC: 0.9950 -> 0.9979Improved
Train with AUM instead of squared hinge all pairs losslinear model · zip 0/1, balanced trainmedian test AUC: 0.9991 -> 0.9993No clear effect
Minimize AUM on predicted values directly (chipseq, 68 train sets)Initial min-label-error predictions · chipseq changepoint train setstrain AUCImproved
Constrain predictions to a linear model when minimizing AUMAUM gradient descent · chipseq H3K4me3_XJ_immune fold 4 (p=27, n=54)train AUCNo clear effect
AUM gradient descent from squared hinge initialization, with early stoppinglinear model · neuroblastoma changepoint (5 train sets)test AUCMixed
Use AUM instead of squared hinge label-error losschangepoint detection · chipseq changepointlabel error rateHurt
Use AUM O(n log n) gradient instead of all-pairs squared hingebinary classification · speed test, 1 second budgetproblem size computable: n=thousands -> n=millionsImproved
Use AUM instead of per-example squared hingechangepoint detection · speed test, n about 5000gradient time: 1ms -> 10msHurt

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