2 papers
cs.LG2026
A Testable Certificate for Constant Collapse in Teacher-Guided VAEs
Zegu Zhang, Jianhua Peng, Jian Zhang
Posterior collapse in variational autoencoders is often diagnosed by its symptoms: a small KL term, a strong decoder, or weak use of the latent code. These signals are useful, but…
cs.CR2026
DPDSyn: Improving Differentially Private Dataset Synthesis for Model Training by Downstream Task Guidance
Mingxuan Jia, Wen Huang, Weixin Zhao +3
How to synthesize a dataset while achieving differential privacy for AI model training is a meaningful but challenging problem. To address this problem, state-of-the-art methods fi…