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:Machine Learning Reading Group @ CUED
SUMMARY:Bayesian Optimization - Pawel Budzianowiski\; Bria
n Trippe
DTSTART;TZID=Europe/London:20161124T133000
DTEND;TZID=Europe/London:20161124T150000
UID:TALK68510AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/68510
DESCRIPTION:Bayesian optimization is a framework for performin
g optimization of black box functions\, which is p
articularly useful when function evaluations are e
xpensive and the space of possible solutions is la
rge. This talk is roughly divided into two parts
\; first we give an overview of Bayesian optimizat
ion\, introducing the approach as well as common f
unction models and acquisition functions. In the
second half of the talk\, we highlight some of the
many recent advances in the field and discuss ope
n problems. Namely\, we will discuss problems in m
ultitask Bayesian optimization\, a recent method o
f modeling a function with Bayesian neural network
s\, and connections with active learning.\nReading
:\nThese will be covered in the talk:\n\nA Recent
Review on Bayesian Optimization\n\nBayesian Optimi
zation with Robust Bayesian Neural Networks (to ap
pear at NIPS 2016)
LOCATION:Engineering Department\, CBL Room 438
CONTACT:Yingzhen Li
END:VEVENT
END:VCALENDAR