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:Statistics
SUMMARY:Distributional learning: from methodology to appli
cations - Xinwei Shen (ETH Zurich)
DTSTART;TZID=Europe/London:20241011T140000
DTEND;TZID=Europe/London:20241011T150000
UID:TALK222040AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/222040
DESCRIPTION:Estimating the full (conditional) distribution is
crucial to many applications. However\, existing m
ethods such as quantile regression typically strug
gle with high-dimensional response variables. To t
his end\, distributional learning models the targe
t distribution via a generative model\, which enab
les inference via sampling. In this talk\, we intr
oduce a distributional learning method called engr
ession. We then demonstrate the applications of en
gression to several statistical problems including
extrapolation in nonparametric regression\, causa
l effect estimation\, and dimension reduction\, as
well as scientific problems such as climate downs
caling.
LOCATION:Centre for Mathematical Sciences MR12\, CMS
CONTACT:Qingyuan Zhao
END:VEVENT
END:VCALENDAR