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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use SOPA for one-way partial AUC optimization | ResNet18 image classifiers · CIFAR-10, CIFAR-100, Melanoma | pAUC | Improved |
| Use SOPA-s for one-way partial AUC optimization | GIN graph classifiers · molmuv(t1), molpcba(t0) | pAUC | Improved |
| Use SOTA-s for two-way partial AUC optimization | image and graph classifiers · all reported TPAUC datasets/settings | pAUC | Improved |
| Tune γ₀ rather than fixing it at 0.9 (ablation) | SOPA-s · CIFAR-10, CIFAR-100, moltox21, molmuv | pAUC | Improved |
| Tune γ₀ and γ₁ rather than fixing both at 0.9 (ablation) | SOTA-s · CIFAR-10, CIFAR-100, moltox21, molmuv | pAUC | Improved |
| Use the KL-regularized soft estimator instead of the CVaR exact estimator | OPAUC optimization · moltox21(t0) | relative error to exact estimator | Mixed |
| Use mini-batch SOPA-s instead of SOPA | OPAUC optimization · training convergence | convergence speed | Improved |
Closest papers by meaning
- Distributionally Robust Optimization with Bias and Variance Reduction (ICLR 2024 · similarity 0.85)
- Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization (AAAI 2024 · similarity 0.85)
- Differentiable Distributionally Robust Optimization Layers (ICML 2024 · similarity 0.84)
- Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.84)
- Efficient Stochastic Approximation of Minimax Excess Risk Optimization (ICML 2024 · similarity 0.84)
- Pairwise AUC Optimization Needs Corrective Power: A Unified View (NeurIPS 2026 · similarity 0.84)
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.
