AI safety researcher

Gerome Miklau

University of Massachusetts Amherst

Google Scholar dblp ORCID Homepage

Latest AI safety papers

On this site: 3 papers

February 2019

Privacy Preserving Off-Policy Evaluation
Feb 1arXiv ↗

June 2017

Differentially Private Learning of Undirected Graphical Models using Collective Graphical Models
Jun 14arXiv ↗

December 2015

Principled Evaluation of Differentially Private Algorithms using DPBench
Dec 15arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.