2 papers
cs.LG2024
Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees
Guang-Yuan Hao, Hengguan Huang, Haotian Wang +2
Active learning (AL) aims to improve model performance within a fixed labeling budget by choosing the most informative data points to label. Existing AL focuses on the single-domai…
cs.LG2023
PAC Privacy Preserving Diffusion Models
Qipan Xu, Youlong Ding, Xinxi Zhang +2
Data privacy protection is garnering increased attention among researchers. Diffusion models (DMs), particularly with strict differential privacy, can potentially produce images wi…