Research map / Optimization / Optimizers
Provable Multi-instance Deep AUC Maximization with Stochastic Pooling
Dixian Zhu, Bokun Wang, Zhi Chen, Yaxing Wang, Milan Sonka, 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 variance-reduced smoothed-max pooling instead of naive mini-batch smoothed-max pooling | DAM on Breast Cancer · Breast Cancer | AUC: 0.725(0.184) -> 0.875(0.137) | Improved |
| Use variance-reduced attention pooling instead of naive mini-batch attention pooling | DAM on Breast Cancer · Breast Cancer | AUC: 0.875(0.112) -> 0.95(0.1) | Improved |
| Use variance-reduced smoothed-max pooling instead of naive mini-batch smoothed-max pooling | DAM on Colon Ade. · Colon Ade. | AUC: 0.905(0.01) -> 0.91(0.02) | Improved |
| Use variance-reduced attention pooling instead of naive mini-batch attention pooling | DAM on Colon Ade. · Colon Ade. | AUC: 0.882(0.029) -> 0.893(0.08) | Improved |
| Use variance-reduced smoothed-max pooling instead of naive mini-batch smoothed-max pooling | DAM on PDGM · PDGM | AUC: 0.659(0.058) -> 0.669(0.032) | Improved |
| Use variance-reduced attention pooling instead of naive mini-batch attention pooling | DAM on PDGM · PDGM | AUC: 0.624(0.112) -> 0.635(0.052) | Improved |
| Use variance-reduced smoothed-max pooling instead of naive mini-batch smoothed-max pooling | DAM on OCT · OCT | AUC: 0.829(0.008) -> 0.848(0.01) | Improved |
| Use variance-reduced attention pooling instead of naive mini-batch attention pooling | DAM on OCT · OCT | AUC: 0.842(0.013) -> 0.843(0.012) | No clear effect |
| Increase instance-batch size B (ablation) | MIDAM · MUSK2 | training convergence speed | Improved |
| Use instance-batch size B=4 rather than all instances per bag (ablation) | MIDAM · MUSK2 | training AUC | No clear effect |
| Allocate fixed total budget with hat B=4 and B=64 (ablation) | MIDAM · Colon Ade. | training convergence speed | Improved |
| Use stochastic instance sampling rather than all-instance pooling | MIDAM on tabular benchmarks · Testing performance | AUC | Mixed |
Closest papers by meaning
- Compositional Training for End-to-End Deep AUC Maximization (ICLR 2022 · similarity 0.88)
- Large-Scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification (ICCV 2021 · similarity 0.87)
- Stochastic AUC Maximization with Deep Neural Networks (ICLR 2020 · similarity 0.87)
- A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep AUC Maximization (ICML 2024 · similarity 0.85)
- Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization (NeurIPS 2024 · similarity 0.83)
- A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning (AAAI 2025 · similarity 0.83)
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.
