all AI news
The Poisson binomial mechanism for secure and private federated learning. (arXiv:2207.09916v1 [cs.CR])
July 21, 2022, 1:11 a.m. | Wei-Ning Chen, Ayfer Özgür, Peter Kairouz
stat.ML updates on arXiv.org arxiv.org
We introduce the Poisson Binomial mechanism (PBM), a discrete differential
privacy mechanism for distributed mean estimation (DME) with applications to
federated learning and analytics. We provide a tight analysis of its privacy
guarantees, showing that it achieves the same privacy-accuracy trade-offs as
the continuous Gaussian mechanism. Our analysis is based on a novel bound on
the R\'enyi divergence of two Poisson binomial distributions that may be of
independent interest.
Unlike previous discrete DP schemes based on additive noise, our mechanism …
More from arxiv.org / stat.ML updates on arXiv.org
Entropic covariance models
3 days, 22 hours ago |
arxiv.org
Uncertainty quantification in metric spaces
3 days, 22 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York