From the 1 of 5 linked papers with an AI index.
5 papers
Segmenting Human-LLM Co-authored Text via Change Point Detection
Mengchu Li, Jin Zhu, Jinglai Li +1
The paper introduces algorithms that locate human-written versus LLM-generated segments within a mixed text by treating the problem as a change‑point detection task, and provides t…
Contaminated Multi-task Learning with Heterogeneity: Fundamental Limits and Optimal Algorithms
Ye Tian, Mengchu Li, Marco Avella Medina
Integrating information across related tasks can improve estimation and prediction in transfer, multi-task, and federated learning, but contamination and heterogeneity make robust…
Online change point detection under heavy-tailedness and contamination
Edwin Yiu Nam Tang, Yudong Chen, Mengchu Li +1
We study an online version of the robust mean change point detection problem under a dynamic Huber contamination model with arbitrary contamination distribution and inlier distribu…
Federated Transfer Learning with Differential Privacy
Mengchu Li, Ye Tian, Yang Feng +1
Federated learning has emerged as a powerful framework for analysing distributed data, yet two challenges remain pivotal: heterogeneity across sites and privacy of local data. In t…
Robust mean change point testing in high-dimensional data with heavy tails
Mengchu Li, Yudong Chen, Tengyao Wang +1
We study mean change point testing problems for high-dimensional data, with exponentially- or polynomially-decaying tails. In each case, depending on the -norm of the mean…