Philippe Rigollet

Associate Professor of Mathematics

Brief Biography

Philippe Rigollet works at the intersection of statistics, machine learning, and optimization, focusing primarily on the design and analysis of statistical methods for high-dimensional problems. His recent research focuses on the statistical limitations of learning under computational constraints.

At the University of Paris VI, Rigollet earned a BS in statistics in 2001, a BS in applied mathematics in 2002, and a PhD in mathematical statistics in 2006 under the supervision of Alexandre Tsybakov. He has held positions as a visiting assistant professor at the Georgia Institute of Technology and then as an assistant professor at Princeton University.

Selected Publications

  • "Online learning in repeated auctions," Jonathan Weed, Vianney Perchet and  Philippe Rigollet (2016), Proceedings of COLT 2016. J. Mach. Learn. Res. W&CP, 49.
  • "Batched Bandit Problems," Vianney Perchet, Philippe Rigollet, Sylvain Chassang, and Erik Snowberg (2016), Ann. Statist., 44(2), 660-681.
  • "Complexity Theoretic Lower Bounds for Sparse Principal Component Detection," Quentin Berthet and Philippe Rigollet (2013), Proceedings of COLT 2013. J. Mach. Learn. Res. W&CP, 30, 1046-1066. Best Paper Award
  • "Optimal detection of sparse principal components in high dimension," Quentin Berthet and Philippe Rigollet (2013), Ann. Statist., 41(1), 1780-1815.
  • "The multi-armed bandit problem with covariates," Vianney Perchet and Philippe Rigollet (2013), Ann. Statist., 41(2), 693-721.

Selected Awards

  • 2016. NEC Corporation Fund for Research in Computers and Communications
  • 2015. Invited lecturer. Machine Learning Summer School, Kyoto, Japan
  • 2013. Best Paper Award. Conference on Learning Theory (COLT)
  • 2013. Howard B. Wentz Jr. Junior Faculty Award
  • 2011. NSF CAREER Award DMS-1053987

Courses Taught

  • 18.650 Statistics for Applications