AI RESEARCH
Nonparametric Variational Differential Privacy via Embedding Parameter Clipping
arXiv CS.LG
•
ArXi:2603.09583v1 Announce Type: new The nonparametric variational information bottleneck (NVIB) provides the foundation for nonparametric variational differential privacy (NVDP), a framework for building privacy-preserving language models. However, the learned latent representations can drift into regions with high information content, leading to poor privacy guarantees, but also low utility due to numerical instability during