BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:When Statistics Meets Computing - Professor Tony Cai (Wharton\, Un
 iversity of Pennsylvania)
DTSTART:20181010T160000Z
DTEND:20181010T170000Z
UID:TALK108859@talks.cam.ac.uk
CONTACT:HoD Secretary\, DPMMS
DESCRIPTION:In the conventional statistical framework\, the goal is develo
 ping optimal inference procedures\, where optimality is understood with re
 spect to the sample size and parameter space. When the dimensionality of t
 he data becomes large as in many contemporary applications\, the computati
 onal concerns associated with the statistical procedures come to the foref
 ront. A fundamental question is: Is there a price to pay for statistical p
 erformance if one only considers computable (polynomial-time) procedures? 
 After all\, statistical methods are useful in practice only if they can be
  computed within a reasonable amount of time. \n\nIn this talk\, we discus
 s the interplay between statistical accuracy and computational efficiency 
 in two specific problems: submatrix localization and sparse matrix detecti
 on based on a noisy observation of a large matrix. The results show some i
 nteresting phenomena that are quite different from other high-dimensional 
 problems studied in the literature.\n\nA wine reception in the central cor
 e will follow the talk. 
LOCATION:Centre for Mathematical Sciences MR2
END:VEVENT
END:VCALENDAR