Privacy-Preserving Belief Propagation and Sampling

We provide provably privacy-preserving versions of belief propagation, Gibbs sampling, and other local algorithms — distributed multiparty protocols in which each party or vertex learns only its final local value, and absolutely nothing else.

• Type: Conference
• Year: 2007
• Where: NIPS
• Authors: Michael Kearns, Jinsong Tan, Jennifer Wortman
• Keywords: Gibbs Sampling, Information Technology, Multiparty Protocols, NIPS 2007, final Local Value