all AI news
Private Estimation with Public Data. (arXiv:2208.07984v1 [cs.LG])
Aug. 18, 2022, 1:10 a.m. | Alex Bie, Gautam Kamath, Vikrant Singhal
cs.LG updates on arXiv.org arxiv.org
We initiate the study of differentially private (DP) estimation with access
to a small amount of public data. For private estimation of d-dimensional
Gaussians, we assume that the public data comes from a Gaussian that may have
vanishing similarity in total variation distance with the underlying Gaussian
of the private data. We show that under the constraints of pure or concentrated
DP, d+1 public data samples are sufficient to remove any dependence on the
range parameters of the private data …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Principal Data Engineering Manager
@ Microsoft | Redmond, Washington, United States
Machine Learning Engineer
@ Apple | San Diego, California, United States