AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee

Dixian Zhu, Gang Li, Bokun Wang, Xiaodong Wu, Tianbao Yang

ICML 2022 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 6 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 SOPA for one-way partial AUC optimizationResNet18 image classifiers · CIFAR-10, CIFAR-100, MelanomapAUCImproved
Use SOPA-s for one-way partial AUC optimizationGIN graph classifiers · molmuv(t1), molpcba(t0)pAUCImproved
Use SOTA-s for two-way partial AUC optimizationimage and graph classifiers · all reported TPAUC datasets/settingspAUCImproved
Tune γ₀ rather than fixing it at 0.9 (ablation)SOPA-s · CIFAR-10, CIFAR-100, moltox21, molmuvpAUCImproved
Tune γ₀ and γ₁ rather than fixing both at 0.9 (ablation)SOTA-s · CIFAR-10, CIFAR-100, moltox21, molmuvpAUCImproved
Use the KL-regularized soft estimator instead of the CVaR exact estimatorOPAUC optimization · moltox21(t0)relative error to exact estimatorMixed
Use mini-batch SOPA-s instead of SOPAOPAUC optimization · training convergenceconvergence speedImproved

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