BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Communication-constrained hypothesis testing: Optimality\, robustn
 ess\, and reverse data processing inequalities - Dr Varun Jog\, University
  of Cambridge
DTSTART:20221019T130000Z
DTEND:20221019T140000Z
UID:TALK182561@talks.cam.ac.uk
CONTACT:Dr Varun Jog
DESCRIPTION:In this talk\, we discuss hypothesis testing under communicati
 on constraints\, where each sample is quantized before being revealed to a
  statistician. We show that the sample complexity of simple binary hypothe
 sis testing under communication constraints is at most a logarithmic facto
 r larger than in the unconstrained setting and this bound is tight. We dev
 elop a polynomial-time algorithm that achieves the aforementioned sample c
 omplexity. Our proofs rely on a new reverse data processing inequality and
  a reverse Markov inequality\, which may be of independent interest. 
LOCATION:MR5\, CMS Pavilion A
END:VEVENT
END:VCALENDAR