4 papers · 1 filter
Efficient machine unlearning with minimax optimality
Jingyi Xie, Linjun Zhang, Sai Li
There is a growing demand for efficient data removal to comply with regulations like the GDPR and to mitigate the influence of biased or corrupted data. This has motivated the fiel…
A Statistical Framework for Alignment with Biased AI Feedback
Xintao Xia, Zhiqiu Xia, Linjun Zhang +1
Modern alignment pipelines are increasingly replacing expensive human preference labels with evaluations from large language models (LLM-as-Judge). However, AI labels can be system…
Statistical Inference for Differentially Private Stochastic Gradient Descent
Xintao Xia, Linjun Zhang, Zhanrui Cai
Privacy preservation in machine learning, particularly through Differentially Private Stochastic Gradient Descent (DP-SGD), is critical for sensitive data analysis. However, existi…
Differentially Private Sliced Inverse Regression: Minimax Optimality and Algorithm
Xintao Xia, Linjun Zhang, Zhanrui Cai
Privacy preservation has become a critical concern in high-dimensional data analysis due to the growing prevalence of data-driven applications. Since its proposal, sliced inverse r…