Advanced Networks Colloquium: Alexandre Proutiere, "Bandit Optimization"
Friday, October 11, 2013
1146 A.V. Williams Building
The Advanced Networks Colloquium
Bandit Optimization with Large Strategy Sets and Applications
School of Electrical Engineering
KTH, the Royal Institute of Technology
| video | < href=http://www.isr.umd.edu/sites/default/files/Alexandre_Proutiere.pdf>slides |
Bandit optimization problems constitute the most fundamental and basic instances of sequential decision problems with an exploration-exploitation trade-off. They naturally arise in many contemporary applications found in communication networks, e-commerce and recommendation systems. In this lecture, we present recent results on bandit optimization problems with large strategy sets. For such problems, the number of possible strategies may not be negligible compared to the time horizon. Results are applied to the design of protocols and resource sharing algorithms in wireless systems.
Alexandre Proutiere graduated in Mathematics from Ecole Normale Superieure (Paris), and got an engineering degree from Ecole Nationale Superieure des Telecoms (Paris). He is an engineer from Corps of Mines, and received his PhD in Applied Mathematics from Ecole Polytechnique, Palaiseau, France in 2003. From 1998 to 2000, he worked in the radio communication department at the Ministry of Foreign Affairs in Paris. He joined James Roberts' research group at France Telecom R&D in 2000. From 2007 to 2011, he held a position of researcher at Microsoft Research in Cambridge (UK). He is now Associate Professor at KTH, Sweden. Alexandre was the recipient in 2009 of the ACM Sigmetrics rising star award, and received twice the best paper awards at ACM Sigmetrics conference, and once at the ACM Mobihoc conference. He is an associate editor of IEEE Transactions on Networking, and of Queueing systems and applications.