BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/132
DTSTAMP:20230914T125911Z
SUMMARY:Polynomial Learning of Distribution Families
DESCRIPTION:Speaker: Kaushik Sinha\nDepartment of Computer Science and\nEng
 ineering\nThe Ohio State University\nEnarson Hall 154 W 12t\n\nAbstract: \
 nThe study of Gaussian mixture distributions goes back to the late 19th ce
 ntury\, when Pearson introduced the method of moments to analyze the stati
 stics of a crab population. They have since become one of the most popular
  tools of modeling and data analysis\, extensively used in speech recognit
 ion\, computer vision and other fields. Yet their properties are still not
  well understood.\n\nIn my talk I will discuss some theoretical aspects of
  the problem of learning Gaussian mixtures. In particular\, I will discuss
  our recent result with Mikhail Belkin\, which\, in a certain sense\, comp
 letes work on an active recent topic in theoretical computer science by es
 tablishing quite general conditions for polynomial learnability of mixture
  distributions.\n
URL:https://www.tcs.tifr.res.in/web/events/132
DTSTART;VALUE=DATE:20101203
LOCATION:A-212 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR