fbpx On representations and fairness: a few information-theoretic tools for machine learning | University of Limerick arrow
Search icon

On representations and fairness: a few information-theoretic tools for machine learning

MACSI at the department of Mathematics and Statistics at the University of Limerick invites you to a seminar

Date:  Tuesday 21st May, Room A2-002 at 2p.m.

Speaker: Prof. Flavio P. Calmon (John A. Paulson School of Engineering and Applied Sciences, Harvard University)

Title: On representations and fairness: a few information-theoretic tools for machine learning

Abstract: 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 and (ii) characterize data representations learned by complex learning models. On the fairness side, we explore how local perturbations of distributions can help both identify proxy features for discrimination as well as repair models for bias. On the representation learning side, we explore a theoretical tool called principal inertia components (PICs),  which enjoy a long history in the statistics and information theory literature. We use the PICs to scale-up a multivariate statistical tool called correspondence analysis (CA) using neural networks, enabling data dependencies to be visualized and interpreted at a large scale. We illustrate these techniques in both synthetic and real-world datasets, and discuss future research directions.

Bio: 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 Google Research Faculty Award, the IBM Open Collaborative Research Award, and Harvard's Lemann Brazil Research Fund Award.

Further Information: If you have any questions regarding this seminar, please direct them to Romina Gaburro (061 2131930, email romina.gaburro@ul.ie  or Clifford Nolan (061 202766), clifford.nolan@ul.ie).

Sfi logo