CISE Seminar: Feb. 22, 2019 – Flavio P. Calmon, Harvard University

BU Photonics Building
8 St. Mary’s Street, PHO 205
3:00pm-4:00pm

Flavio P. Calmon
Harvard University

Representations, Fairness, and Privacy: Information-Theoretic Tools for Machine Learning 

Information theory can shed light on the algorithm-independent limits of learning from data and serve as a design driver for new machine learning algorithms. In this talk, we discuss a set of information-theoretic tools that can be used to (i) help understand fairness and discrimination in machine learning, (ii) characterize data representations learned by complex learning models, and (time permitting) (iii) understand fundamental trade-offs between privacy and utility. One of the main tools we use is called the principal inertia components,  which enjoy a long history in the statistics and information theory literature, and provide a fine-grained decomposition of the dependence between two random variables. We illustrate these techniques in both synthetic and real-world datasets, and discuss future research directions.

Flavio P. Calmon is an Assistant Professor of Electrical Engineering at Harvard’s John A. Paulson School of Engineering and Applied Sciences. Before joining Harvard, he was the inaugural data science for social good post-doctoral fellow at  IBM Research in Yorktown Heights, New York. He received his Ph.D. in Electrical Engineering and Computer Science at MIT. His main research interests are information theory, inference, and statistics, with applications to fairness, privacy, machine learning, and communications engineering. Prof. Calmon has received the NSF CAREER award, the IBM Open Collaborative Research Award, and Harvard’s Lemann Brazil Research Fund Award.