4 papers
cs.LG2025
Learning to Rank with Top- Fairness
Boyang Zhang, Quanqi Hu, Mingxuan Sun +2
Fairness in ranking models is crucial, as disparities in exposure can disproportionately affect protected groups. Most fairness-aware ranking systems focus on ensuring comparable a…
math.OC2024
Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions
Quanqi Hu, Qi Qi, Zhaosong Lu +1
In this paper, we study a class of non-smooth non-convex problems in the form of , where both $Φ(x) = \max_{y\in Y}Ï(x, y…
math.OC2024
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…
cs.LG2024
Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning
Qi Qi, Quanqi Hu, Qihang Lin +1
This paper studies learning fair encoders in a self-supervised learning (SSL) setting, in which all data are unlabeled and only a small portion of them are annotated with sensitive…