In this talk, I’ll give an introduction to differential privacy with an emphasis on its relationship to machine learning, and its usefulness outside of privacy. Along the way, I’ll give a taste for the mathematical tools that can be used to achieve differential privacy. My thesis is that anyone who cares about data should care about the tools that the differential privacy literature offers.
Katrina Ligett is an assistant professor of computer science and economics at Caltech. Before joining Caltech in 2011, she did postdoctoral work at Cornell, and she received her PhD in computer science from Carnegie Mellon in 2009. Her primary research interests are in mathematical foundations for data privacy, and in game theory. She has received an NSF Career Award, a Microsoft Research Faculty Fellowship, a Google Faculty Research Award, and an Okawa Foundation Research Grant.