BEGIN:VCALENDAR
METHOD:PUBLISH
VERSION:2.0
PRODID:-//Cornell U. Department of Computer Science//Brown Bag Seminar//EN
BEGIN:VEVENT
SUMMARY:Brown bag: Andrew Wilson
DESCRIPTION:Title: How Do We Build Models that Learn and
	 Generalize?\nSpeaker: Andrew Wilson\nAbstract: To answer scientific
	 questions\, and reason about data\, we must build models and perform
	 inference within those models.  But how should we approach model
	 construction and inference to make the most successful predictions?  How
	 do we represent uncertainty and prior knowledge?  How flexible should
	 our models be?  Should we use a single model\, or multiple different
	 models?  Should we follow a different procedure depending on how much
	 data are available?\n\nIn this talk I will present a philosophy for
	 model construction\, grounded in probability theory.  I will then
	 discuss recent works in my group that exemplify this philosophy: (1)
	 constant-time predictive distributions for Gaussian processes ; (2)
	 probabilistic word embeddings; (3) our just-released paper on loss
	 surfaces\, mode connectivity\, and fast ensembling of deep neural
	 networks.
LOCATION:Gates 122
UID:2018-03-06
STATUS:CONFIRMED
DTSTART:20180306T170000Z
DTEND:20180306T180000Z
LAST-MODIFIED:20180305T151808Z
ORGANIZER;CN=Jonathan Shi:http://www.cs.cornell.edu/~jshi/brownbag/
DTSTAMP:20260408T173111Z
END:VEVENT
END:VCALENDAR