51ÂÜÀò

Fisher Information Under Local Differential Privacy

Submitted by admin on Mon, 10/28/2024 - 01:24

We develop data processing inequalities that describe how Fisher information from statistical samples can scale with the privacy parameter $\varepsilon $ under local differential privacy constraints. These bounds are valid under general conditions on the distribution of the score of the statistical model, and they elucidate under which conditions the dependence on $\varepsilon $ is linear, quadratic, or exponential.

Committee members 38790

Anand D. Sarwate
Associate Professor
Department of Electrical and Computer Engineering
Rutgers, The State University of New Jersey
94 Brett Road.
Piscataway, NJ 08854
Phone: (848) 445-8516