Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Ullman, Jon"'
In this work, we study local minimax convergence estimation rates subject to $\epsilon$-differential privacy. Unlike worst-case rates, which may be conservative, algorithms that are locally minimax optimal must adapt to easy instances of the problem.
Externí odkaz:
http://arxiv.org/abs/2210.15819
Autor:
Ullman, Jonathan Robert
As both the scope and scale of data collection increases, an increasingly large amount of sensitive personal information is being analyzed. In this thesis, we study the feasibility of effectively carrying out such analyses while respecting the privac
Externí odkaz:
http://dissertations.umi.com/gsas.harvard:10992
http://nrs.harvard.edu/urn-3:HUL.InstRepos:11041647
http://nrs.harvard.edu/urn-3:HUL.InstRepos:11041647