Best paper for Berthet, Rigollet

April 26, 2013

Graduate student Quentin Berthet and Assistant Professor Philippe Rigollet will receive the "best paper award" at this year's edition of the Conference On Learning Theory (COLT) for their paper "Complexity Theoretic Lower Bounds for Sparse Principal Component Detection". In this groundbreaking work, they show that employing computationally efficient statistical methods in the context of sparse principal component analysis leads to an ineluctable deterioration of statistical performance, regardless of the efficient method employed. In particular, their paper draw new connections between statistical learning and computational complexity.

For the full list of accepted papers, visit the COLT 2013 website.