9 citations · 23 across the 7 of their papers we have counts for
7 papers
Gradient Aligned Regression via Pairwise Losses
Dixian Zhu, Tianbao Yang, Livnat Jerby
Regression is a fundamental task in machine learning that has garnered extensive attention over the past decades. The conventional approach for regression involves employing loss f…
Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization
Quanqi Hu, Dixian Zhu, Tianbao Yang
This paper investigates new families of compositional optimization problems, called on-mooth eakly-onvex…
Provable Multi-instance Deep AUC Maximization with Stochastic Pooling
Dixian Zhu, Bokun Wang, Zhi Chen +4
This paper considers a novel application of deep AUC maximization (DAM) for multi-instance learning (MIL), in which a single class label is assigned to a bag of instances (e.g., mu…
LibAUC: A Deep Learning Library for X-Risk Optimization
Zhuoning Yuan, Dixian Zhu, Zi-Hao Qiu +3
This paper introduces the award-winning deep learning (DL) library called LibAUC for implementing state-of-the-art algorithms towards optimizing a family of risk functions named X-…
Benchmarking Deep AUROC Optimization: Loss Functions and Algorithmic Choices
Dixian Zhu, Xiaodong Wu, Tianbao Yang
The area under the ROC curve (AUROC) has been vigorously applied for imbalanced classification and moreover combined with deep learning techniques. However, there is no existing wo…
When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee
Dixian Zhu, Gang Li, Bokun Wang +2
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 prop…
Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
Dixian Zhu, Yiming Ying, Tianbao Yang
We study a family of loss functions named label-distributionally robust (LDR) losses for multi-class classification that are formulated from distributionally robust optimization (D…