3 papers
cs.LG2025
Understanding Private Learning From Feature Perspective
Meng Ding, Mingxi Lei, Shaopeng Fu +3
Differentially private Stochastic Gradient Descent (DP-SGD) has become integral to privacy-preserving machine learning, ensuring robust privacy guarantees in sensitive domains. Des…
cs.LG2025
Towards User-level Private Reinforcement Learning with Human Feedback
Jiaming Zhang, Mingxi Lei, Meng Ding +5
Reinforcement Learning with Human Feedback (RLHF) has emerged as an influential technique, enabling the alignment of large language models (LLMs) with human preferences. Despite th…
cs.CV2024
TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram
Mingxi Lei, Chunwei Ma, Meng Ding +3
Deep learning models often struggle with generalization when deploying on real-world data, due to the common distributional shift to the training data. Test-time adaptation (TTA) i…