A Simple and Practical Algorithm for Differentially Private Data Release

 

 

Katrina Ligett
Assistant Professor of Computer Science and Economics
Caltech

Wednesday, October 10, 2012
4:00pm 5130
Upson Hall

 

Abstract:

 

In this talk, we present a new algorithm for differentially private data release, based on a simple combination of the Exponential Mechanism with the Multiplicative Weights update rule. Our algorithm achieves what are the best known and nearly optimal theoretical guarantees, while at the same time being simple to implement and experimentally more accurate on actual data sets than existing techniques.

The talk will incorporate brief tutorials on differential privacy and on multiplicative weights; no knowledge of either is assumed.

Joint work with Moritz Hardt and Frank McSherry.

Paper at: http://arxiv.org/abs/1012.4763