More Like this

1. Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraints

   Yao, Y.; Lin, Q.; Yang, T. (January 2023, International Conference on Artificial Intelligence and Statistics (AISTATS))
2. Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraints

   Yao, Yao; Lin, Qihang; Yang, Tianbao (April 2023, AIStats)
3. Federated Compositional Deep AUC Maximization

   Zhang, Xinwen; Zhang, Yihan; Yang, Tianbao; Souvenir, Richard; Gao, Hongchang (December 2023, Neural Information Processing Systems)
4. When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee

   Zhu, Dixian and (July 2022, Proceedings of the 39th International Conference on Machine Learning)

   Chaudhuri, Kamalika and (Ed.)

   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. 

   more » « less
5. Stochastic AUC optimization with general loss

   https://doi.org/10.3934/cpaa.2020188  

   Yang, Zhenhuan; Shen, Wei; Ying, Yiming; Yuan, Xiaoming (January 2020, Communications on Pure & Applied Analysis)