Timezone: »

 
Improved Privacy Filters and Odometers: Time-Uniform Bounds in Privacy Composition
Justin Whitehouse · Aaditya Ramdas · Ryan Rogers · Steven Wu

In this work, we leverage recent advances in time-uniform supermartingale concentration to provide a unified analysis for advanced privacy composition, privacy filters, and privacy odometers. As a consequence, we are able to construct improved privacy filters and odometers for fully adaptive private data analysis.

Author Information

Justin Whitehouse (School of Computer Science, Carnegie Mellon University)
Aaditya Ramdas (Carnegie Mellon University)

Aaditya Ramdas is an assistant professor in the Departments of Statistics and Machine Learning at Carnegie Mellon University. These days, he has 3 major directions of research: 1. selective and simultaneous inference (interactive, structured, post-hoc control of false discovery/coverage rate,…), 2. sequential uncertainty quantification (confidence sequences, always-valid p-values, bias in bandits,…), and 3. assumption-free black-box predictive inference (conformal prediction, calibration,…).

Ryan Rogers (LinkedIn)
Steven Wu (Carnegie Mellon University)

More from the Same Authors