Professor Calmon’s research explores the interplay between information theory, machine learning and statistics, focusing on applications in data science, content distribution, privacy and security.

Before joining Harvard Professor Calmon was a 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 the Massachusetts Institute of Technology, an M.Sc. in Electrical Engineering at the Universidade Estadual de Campinas in Campinas, Brazil, and a B.Sc. in Communications Engineering at the Universidade de Brasília in Brasília, Brazil. Before joining Harvard he was a Social Good Post-Doctoral Fellow at the IBM T.J. Watson Research Center in New York.

Prof. Calmon’s research has three intertwined goals: (i) develop theory and models that capture the fundamental limits of estimation and learning from data, (ii) construct learning, security and privacy mechanisms with performance guarantees based on these limits, and (iii) use this methodology as a design driver for future information processing and content distribution systems. In order to achieve these goals, he draws from the fields of information theory, statistics, cryptography and machine learning. He seeks to develop tools that will guide the design of systems that acquire, process and distribute information while providing reliability, efficiency, and privacy guarantees.