BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20190331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20181028T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260404T015848Z
UID:5c3c53babf1ca995474816@ist.ac.at
DTSTART:20190304T090000
DTEND:20190304T100000
DESCRIPTION:Speaker: Yuxin Chen\nhosted by Vladimir Kolmogorov\nAbstract: H
 ow can we intelligently acquire information for decision making\, when fac
 ing a large volume of data? In this talk\, I will focus on learning and de
 cision making problems that arise in robotics\, scientific discovery and h
 uman-centered systems\, and present how we can develop principled approach
 es that actively extract information\, identify the most relevant data for
  the learning tasks and make effective decisions under uncertainty. As an 
 example\, I will introduce the optimal value of information problem for de
 cision making\, and show that for a large class of adaptive information ac
 quisition problems that are known to be NP-hard\, one could devise efficie
 nt surrogate objectives that are amenable to greedy optimization\, while s
 till achieving strong approximation guarantees.I will further talk about a
  few practical challenges in real-world decision-making systems such as co
 mplex constraints\, complex action space\, and rich interfaces. More concr
 etely\, I will elaborate on how to address these practical concerns throug
 h a variety of applications\, ranging from sequential experimental design 
 for scientific discovery to interactive machine teaching for human learner
 s.
LOCATION:Mondi Seminar Room 2\, Central Building\, ISTA
ORGANIZER:tguggenb@ist.ac.at
SUMMARY:Yuxin Chen: Interactive Learning and Decision Making with Machines 
 and People
URL:https://talks-calendar.ista.ac.at/events/1757
END:VEVENT
END:VCALENDAR
