BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME: LMSS @ Cornell Tech: David Blei (Columbia University)
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260906T144146Z
UID:tag:localist.com\,2008:EventInstance_40862204360065
DTSTART:20230428T163000Z
DTEND:20230428T173000Z
DESCRIPTION:Learning Machines Seminar Series\n\nWhat: LMSS: David Blei (Col
 umbia University)\nWhen: Friday\, April 28\, 12:30 p.m. \nWhere: Room 091\
 , Bloomberg Center\, Cornell Tech (map)\nPizza will be served at 12:15 p.m
 .\n\n \n\n"Scaling and generalizing approximate Bayesian inference"\n\nA c
 ore problem in statistics and machine learning is to approximate difficult
 -to-compute probability distributions. This problem is especially importan
 t in Bayesian statistics\, which frames all inference about unknown quanti
 ties as a calculation about a conditional distribution. In this talk I rev
 iew and discuss innovations in variational inference (VI)\, a method a tha
 t approximates probability distributions through optimization. VI has been
  used in myriad applications in machine learning and Bayesian statistics. 
 It tends to be faster than more traditional methods\, such as Markov chain
  Monte Carlo sampling.\n\nAfter quickly reviewing the basics\, I will disc
 uss two lines of research in VI.  I first describe stochastic variational 
 inference\, an approximate inference algorithm for handling massive datase
 ts\, and demonstrate its application to probabilistic topic models of mill
 ions of articles. Then I discuss black box variational inference\, a gener
 ic algorithm for approximating the posterior.  Black box inference easily 
 applies to many models but requires minimal mathematical work to implement
 .  I will demonstrate black box inference on deep exponential families---a
  method for Bayesian deep learning---and describe how it enables powerful 
 tools for probabilistic programming.\n\n \n\nBIO\n\nDavid Blei is a Profes
 sor of Statistics and Computer Science at Columbia University\, and a memb
 er of the Columbia Data Science Institute. He studies probabilistic machin
 e learning and Bayesian statistics\, including theory\, algorithms\, and a
 pplication. David has\nreceived several awards for his research. He receiv
 ed a Sloan Fellowship (2010)\, Office of Naval Research Young Investigator
  Award (2011)\, Presidential Early Career Award for Scientists and Enginee
 rs (2011)\, Blavatnik Faculty Award (2013)\, ACM-Infosys Foundation Award 
 (2013)\, a Guggenheim fellowship (2017)\, and a Simons Investigator Award 
 (2019). He is the co-editor-in-chief of the Journal of Machine Learning Re
 search.  He is a fellow of the Association for Computing Machinery (ACM) a
 nd the Institute of Mathematical Statistics (IMS).
GEO:40.754684;-73.956188
LOCATION:Cornell Tech
SUMMARY: LMSS @ Cornell Tech: David Blei (Columbia University)
URL;VALUE=URI:https://events.cornell.edu/event/lmss_cornell_tech_david_blei
 _columbia
CATEGORIES:Seminar
END:VEVENT
END:VCALENDAR