AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Large-scale Optimization of Partial AUC in a Range of False Positive Rates

Yao Yao, Qihang Lin, Tianbao Yang

NeurIPS 2022 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 5 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
AGD-SBCD instead of SVMpAUC-tight (train)linear model on CheXpert · CheXpert D1 trainpAUC: 0.6259 -> 0.7005Improved
AGD-SBCD instead of SVMpAUC-tight (train)linear model on CheXpert · CheXpert D2 trainpAUC: 0.5860 -> 0.7214Improved
AGD-SBCD instead of SVMpAUC-tight (train)linear model on CheXpert · CheXpert D3 trainpAUC: 0.3745 -> 0.4910Improved
AGD-SBCD instead of SVMpAUC-tight (train)linear model on CheXpert · CheXpert D4 trainpAUC: 0.3895 -> 0.4616Improved
AGD-SBCD instead of SVMpAUC-tight (train)linear model on CheXpert · CheXpert D5 trainpAUC: 0.7267 -> 0.8272Improved
AGD-SBCD vs DCA and proximal DCA, training convergencelinear model on CheXpert · CheXpert trainingtraining loss and pAUCImproved
AGD-SBCD instead of SVMpAUC-tight (test)linear model · CheXpert D4 testpAUC: 0.6521 -> 0.6340Hurt
AGD-SBCD instead of DCA (test)linear model · CheXpert D3 testpAUC: 0.7427 -> 0.8016Improved
AGD-SBCD instead of MB (test)DenseNet121 · CheXpert D3 testpAUC: 0.6339 -> 0.8689Improved
AGD-SBCD instead of CE (test)DenseNet121 · CheXpert D1 testpAUC: 0.6994 -> 0.7535Improved
AGD-SBCD instead of AUC-M (test)DenseNet121 · CheXpert D3 testpAUC: 0.8533 -> 0.8689Improved
AGD-SBCD instead of AUC-M (test)DenseNet121 · CheXpert D5 testpAUC: 0.8504 -> 0.8513No clear effect

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