BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Exact Bayesian Inference for Big Data: Single- and
  Multi-Core Approaches - Murray Pollock (Universit
 y of Warwick)
DTSTART;TZID=Europe/London:20170705T133000
DTEND;TZID=Europe/London:20170705T141500
UID:TALK73157AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/73157
DESCRIPTION:<span>Co-authors: Hongsheng Dai		(Essex)\, Paul Fe
 arnhead		(Lancaster)\, Adam Johansen		(Warwick)\, 
 Divakar Kumar		(Warwick)\, Gareth Roberts		(Warwic
 k)        <br></span><span><br>This talk will intr
 oduce novel methodologies for exploring posterior 
 distributions by modifying methodology for exactly
  (without error) simulating diffusion sample paths
 . The methodologies discussed have found particula
 r applicability to "Big Data" problems. We begin b
 y presenting the Scalable Langevin Exact Algorithm
  (ScaLE) and recent methodological extensions (inc
 luding Re-ScaLE\, which avoids the need for partic
 le approximation in ScaLE)\, which has remarkably 
 good scalability properties as the size of the dat
 a set increases (it has sub-linear cost\, and pote
 ntially no cost as a function of data size). ScaLE
  has particular applicability in the &ldquo\;singl
 e-core&rdquo\; big data setting - in which inferen
 ce is conducted on a single computer. In the secon
 d half of the talk we will present methodology to 
 exactly recombine inferences on separate data sets
  computed on separate cores - an exact version of 
 &ldquo\;divide and conquer". As such this approach
  has particu lar applicability in the &ldquo\;mult
 i-core&rdquo\; big data setting. We conclude by co
 mmenting on future work on the confluence of these
  approaches. Joint work with Hongsheng Dai\, Paul 
 Fearnhead\, Adam Johansen\, Divakar Kumar\, Gareth
  Roberts.</span>
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:INI IT
END:VEVENT
END:VCALENDAR
