Description

 

In this talk, I will explore some recent work of my own and others on optimal estimation under different local privacy constraints. As part of this, we will explore definitions of optimality for statistical estimators—including notions of instance optimality arising out of classical Fisher information—and their connections with privacy. I will also describe recent work developing optimal algorithms for large-scale model fitting and federated learning under local privacy.

All scheduled dates:

Upcoming

No Upcoming activities yet