Algorithms for privacy-preserving machine learning

Tuesday, November 27, 2012

The large-scale gathering and storage of personal data is raising new questions about the regulation of privacy.  On the technology side, there has been a flurry of recent work on new models for privacy risk and protection.  One such model is differential privacy, which quantifies the risk to an individual's data being included in a database.  Differentially private algorithms introduce noise into their computations to limit this risk, allowing the output to be released publicly.  I will describe new algorithms for differentially private machine learning tasks such as learning a classifier and principle components analysis (PCA).  I will describe how guaranteeing privacy affects the performance of these algorithms, the results on real data sets, and some exciting future directions.Parts of this work are with Kamalika Chaudhuri, Claire Monteleoni, Kaushik Sinha, Staal Vinterbo, and Aziz Boxwala.


Postdoctoral Researcher

Bio:Anand Sarwate is currently a Postdoctoral researcher at the Information Theory and Applications Center at the University of California, San Diego. He earned BS degrees in Electrical Engineering and Mathematics from MIT in 2002 and MS and PhD degrees in Electrical Engineering from the University of California, Berkeley in 2005 and 2008, where he was under the supervision of Professor Michael Gastpar. Dr. Sarwate received the Samuel Silver Memorial Scholarship Award and Demetri Angelakos Memorial Achievement Award from the EECS Department at UC Berkeley. His research interests include information theory, distributed signal processing, machine learning, communications, and randomized algorithms for communications and signal processing in sensor networks.