Matthias Grossglauser

Matthias Grossglauser is a Professor of Computer and Communication Sciences at EPFL in Lausanne, Switzerland, where he co-directs the Information and Network Dynamics lab. His current research interests center on machine learning, stochastic networks, and discrete choice models, and on their applications in artificial intelligence, network science, computational social sciences, and recommender systems.

He is a member of the Federal Communications Commission (ComCom), the independent regulatory authority for the Swiss telecommunications market. He was the director of EPFL's Doctoral School in Computer and Communication Sciences (2016-2019). From 2007-2010, he was with the Nokia Research Center (NRC) in Helsinki, Finland, leading the Internet Laboratory, a research organization comprising seven teams in security, networking, social media, and user experience. He was also in charge of a tech-transfer program focused on applied data mining and machine learning, and served on Nokia's CEO Technology Council, a team of technology experts advising the Nokia CEO. Prior to this, he was Assistant Professor at EPFL, and Principal Research Scientist in the Networking and Distributed Systems Laboratory at AT&T Research (Shannon Labs) in New Jersey, USA. He holds a Ph.D. degree in Computer Science from Sorbonne Universités, a M.Sc. degree in Electrical Engineering from Georgia Institute of Technology, and an engineering degree in Communication Systems from EPFL. He is a Fellow of the IEEE and of ELLIS, and the recipient of the 1998 Cor Baayen Award from the European Research Consortium for Informatics and Mathematics (ERCIM) and of the 2006 CoNEXT/SIGCOMM Rising Star Award.

Teaching & PhD

Teaching

Communication Systems

Computer Science

PhD Students

Aboueimehrizi Amir Mohammad, Khorasani Mohammadsadegh, Kuroda Daichi, Villemaud Oscar Jean Olivier,

Past EPFL PhD Students

Chumbalov Daniyar , Etter Vincent , Kafsi Mohamed , Kazemi Ehsan , Ko Young Jun , Kristof Victor , Maystre Lucas , Pedarsani Pedram , Suresh Aswin , Trouleau William , Tschopp Dominique Florian , Yartseva Lyudmila ,

Courses

Internet analytics

Networks out of control

The goal of this class is to acquire mathematical tools and engineering insight about networks whose structure is random, as well as learning and control techniques applicable to such network data.

Principles of online decision-making

This course provides a mathematical treatment of online decision-making. It covers bandits (multi-armed, contextual, structured), Markov Decision Processes (MDPs), and related topics. Key concepts include exploration-exploitation, UCB, Thompson sampling, and tools to derive regret bounds.

Matthias Grossglauser

Full Professor

Fields of expertise

Biography