Algorithms & Randomness Center (ARC)
Kunal Talwar (Google)
Monday, April 1, 2019
Klaus 1116E - 11:00 am
Title: Amplification Theorems for Differentially Private Machine Learning
Abstract: A rigorous foundational approach to private data analysis has emerged in theoretical computer science in the last decade, with differential privacy and its close variants playing a central role. We have recently been able to train complex machine learning models with little accuracy loss, while giving strong differentially privacy guarantees. The analyses of these algorithms rely on a class of results known as privacy amplification theorems. In this talk, I will sketch how private ML models can be trained, and how they can be analysed. I will then describe two recent privacy amplification theorems, and some of their implications.
(Joint works with Ulfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan and Abhradeep Thakurta)
Videos of recent talks are available at: https://smartech.gatech.edu/handle/1853/46836