Timezone: »

Private and Communication-Efficient Algorithms for Entropy Estimation
Gecia Bravo-Hermsdorff · Róbert Busa-Fekete · Mohammad Ghavamzadeh · Andres Munoz Medina · Umar Syed

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #741

Modern statistical estimation is often performed in a distributed setting where each sample belongs to single user who shares their data with a central server. Users are typically concerned with preserving the privacy of their sample, and also with minimizing the amount of data they must transmit to the server. We give improved private and communication-efficient algorithms for estimating several popular measures of the entropy of a distribution. All of our algorithms have constant communication cost and satisfy local differential privacy. For a joint distribution on several variables whose conditional independence graph is a tree, we describe algorithms for estimating Shannon entropy that require a number of samples that is linear in the number of variables, compared to the quadratic sample complexity of prior work. We also describe an algorithm for estimating Gini entropy whose sample complexity has no dependence on the support size of the distribution and can be implemented using a single round of concurrent communication between the users and the server, while the previously best-known algorithm has high communication cost and requires the server to facilitate interaction between the users. Finally, we describe an algorithm for estimating collision entropy that matches the space and sample complexity of the best known algorithm but generalizes it to the private and communication-efficient setting.

Author Information

Gecia Bravo-Hermsdorff (UCL, department of statistics)
Róbert Busa-Fekete (Google Research)
Mohammad Ghavamzadeh (Google Research)
Andres Munoz Medina (Google)
Umar Syed (Google Research)

More from the Same Authors