4 papers · 1 filter
Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
Xiaopu Wang, Zelin He, Chengyuan Liu +1
Logit-based watermarking is a widely used mechanism for identifying LLM generated content, yet its effectiveness is governed by a fundamental trade-off between detectability and se…
Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees
Xin Yu, Zelin He, Ying Sun +2
Personalized federated learning (PFL) offers a flexible framework for aggregating information across distributed clients with heterogeneous data. This work considers a personalized…
TransFusion: Covariate-Shift Robust Transfer Learning for High-Dimensional Regression
Zelin He, Ying Sun, Jingyuan Liu +1
The main challenge that sets transfer learning apart from traditional supervised learning is the distribution shift, reflected as the shift between the source and target models and…
AdaTrans: Feature-wise and Sample-wise Adaptive Transfer Learning for High-dimensional Regression
Zelin He, Ying Sun, Jingyuan Liu +1
We consider the transfer learning problem in the high dimensional linear regression setting, where the feature dimension is larger than the sample size. To learn transferable infor…