BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//MIT Statistics and Data Science Center - ECPv5.10.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:MIT Statistics and Data Science Center
X-ORIGINAL-URL:https://stat.mit.edu
X-WR-CALDESC:Events for MIT Statistics and Data Science Center
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20180311T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20181104T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20180504T110000
DTEND;TZID=America/New_York:20180504T120000
DTSTAMP:20211130T224227
CREATED:20171215T163503Z
LAST-MODIFIED:20180502T144713Z
UID:2298-1525431600-1525435200@stat.mit.edu
SUMMARY:Size-Independent Sample Complexity of Neural Networks
DESCRIPTION:Abstract: I’ll describe new bounds on the sample complexity of deep neural networks\, based on the norms of the parameter matrices at each layer. In particular\, we show how certain norms lead to the first explicit bounds which are fully independent of the network size (both depth and width)\, and are therefore applicable to arbitrarily large neural networks. These results are derived using some novel techniques\, which may be of independent interest.\nJoint work with Noah Golowich (Harvard) and Alexander Rakhlin (MIT) \nBiography: Ohad Shamir is a faculty member in the Department of Computer Science and Applied Mathematics at the Weizmann Institute of Science\, Israel. His research focuses on machine learning\, with emphasis on algorithms which combine practical efficiency and theoretical insight. He is also interested in the many intersections of machine learning with related fields\, such as optimization\, statistics\, theoretical computer science and AI. He has served as program co-chair of COLT 2017\, and is currently a member of the COLT steering committee.
URL:https://stat.mit.edu/calendar/stochastics-statistics-seminar-3/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar
GEO:42.3620185;-71.0878444
END:VEVENT
END:VCALENDAR