Sébastien Bubeck

Portrait 
Researcher

Theory Group, Microsoft Research, Redmond

Contact

Building 99, 2955

Redmond, WA 98052

sebubeck AT microsoft DOT com

I was co-general chair for COLT 2013, COLT 2014, and I am/was on the program committee for NIPS 2012, NIPS 2014, NIPS 2016, COLT 2013, COLT 2014, COLT 2015, COLT 2016, ICML 2015, ICML 2016, ALT 2013, ALT 2014. I am also on the steering committee for COLT.

Currently I'm especially interested in (i) the interplay between convexity and randomness in optimization, and (ii) inference problems on random graphs.

NEW: polynomial-time algorithm for bandit convex optimization

From July 2014 to July 2016 with various co-authors at MSR we dedicated a lot of energy to bandit convex optimization. The end product is a new efficient algorithm. To learn more about it I recommend to first take a look at this [youtube video], then these 3 blog posts ([part 1], [part 2], [part 3]), and finally [the paper] itself.

Research Interests

  • machine learning

  • convex optimization

  • multi-armed bandits

  • statistical network analysis

  • random graphs and random matrices

  • applications of information theory to learning, optimization, and probability