Preprint
When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee
ArXiv.org
02/28/2022
Abstract
In this paper, we propose systematic and efficient gradient-based methods for both one-way and two-way partial AUC (pAUC) maximization that are applicable to deep learning. We propose new formulations of pAUC surrogate objectives by using the distributionally robust optimization (DRO) to define the loss for each individual positive data. We consider two formulations of DRO, one of which is based on conditional-value-at-risk (CVaR) that yields a non-smooth but exact estimator for pAUC, and another one is based on a KL divergence regularized DRO that yields an inexact but smooth (soft) estimator for pAUC. For both one-way and two-way pAUC maximization, we propose two algorithms and prove their convergence for optimizing their two formulations, respectively. Experiments demonstrate the effectiveness of the proposed algorithms for pAUC maximization for deep learning on various datasets.
Details
- Title: Subtitle
- When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee
- Creators
- Dixian ZhuGang LiBokun WangXiaodong WuTianbao Yang
- Resource Type
- Preprint
- Publication Details
- ArXiv.org
- ISSN
- 2331-8422
- Number of pages
- 29 pages
- Language
- English
- Date posted
- 02/28/2022
- Academic Unit
- The Iowa Institute for Biomedical Imaging; Electrical and Computer Engineering; Computer Science; Radiation Oncology
- Record Identifier
- 9984222737702771
Metrics
28 Record Views