8 papers
Tolerance-Based Fairness Auditing: Violation Certification and Sensitivity Screening
Jie Tang, Chuanlong Xie, Lixing Zhu
As artificial intelligence is increasingly deployed, algorithmic unfairness has raised growing concerns and intensified demands for transparent fairness auditing. In practice, the…
A Unified Framework for In-Context Learning with Causal and Masked Language Models
Chenrui Liu, Chuanlong Xie, Falong Tan +2
In-context learning (ICL) has emerged as a central capability of pretrained language models, yet its theoretical analysis has focused primarily on causal language models trained by…
Empirical Likelihood-Based Fairness Auditing: Distribution-Free Certification and Flagging
Jie Tang, Chuanlong Xie, Xianli Zeng +1
Machine learning models in high-stakes applications, such as recidivism prediction and automated personnel selection, often exhibit systematic performance disparities across sensit…
Benchmarking Out-of-Distribution Detection for Plankton Recognition: A Systematic Evaluation of Advanced Methods in Marine Ecological Monitoring
Yingzi Han, Jiakai He, Chuanlong Xie +1
Automated plankton recognition models face significant challenges during real-world deployment due to distribution shifts (Out-of-Distribution, OoD) between training and test data.…
In-Context Learning as Nonparametric Conditional Probability Estimation: Risk Bounds and Optimality
Chenrui Liu, Falong Tan, Chuanlong Xie +2
This paper investigates the expected excess risk of in-context learning (ICL) for multiclass classification. We formalize each task as a sequence of labeled examples followed by a…
DSDE: Using Proportion Estimation to Improve Model Selection for Out-of-Distribution Detection
Jingyao Geng, Yuan Zhang, Jiaqi Huang +4
Model library is an effective tool for improving the performance of single-model Out-of-Distribution (OoD) detector, mainly through model selection and detector fusion. However, ex…
Provable Contrastive Continual Learning
Yichen Wen, Zhiquan Tan, Kaipeng Zheng +2
Continual learning requires learning incremental tasks with dynamic data distributions. So far, it has been observed that employing a combination of contrastive loss and distillati…
Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion
Jiawei Li, Sitong Li, Shanshan Wang +3
Deploying machine learning in open environments presents the challenge of encountering diverse test inputs that differ significantly from the training data. These out-of-distributi…