BEGIN:VCALENDAR
PRODID:-//AddEvent Inc//AddEvent.com v1.7//EN
VERSION:2.0
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20241103T010000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240310T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240329T003045Z
STATUS:CONFIRMED
UID:1711672245addeventcom
SEQUENCE:0
DTSTART;TZID=America/New_York:20221207T160000
DTEND;TZID=America/New_York:20221207T170000
SUMMARY:FDS Seminar: John Langford
DESCRIPTION:FDS Seminar: “Discovering an Agent’s Configuration Space” \n\nSpeaker: John Langford \nMicrosoft Research New York \n\nThis is an in-person seminar.\nWebcast https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=1a9628bf-c5c4-4830-948b-af420136ee87\n\nAbstract: Given potentially very rich and redundant sensory information which an agent receives\, can the agent discover a configuration space summarizing all the configurations it can achieve in an environment? In 2-d free space this could be x\,y\,theta\, but in environments with walls\, movable objects\, and other agents how can this be done? I’ll discuss a basic principle\, theory\, and experimental results suggesting this may be viable for _all_ agents with relatively few environment interactions. \n\nBio: John Langford is a computer scientist working in machine learning and learning theory\, a field that he says “is shifting from an academic discipline to an industrial tool”. \n\nHe is well known for work on the Isomap embedding algorithm\, CAPTCHA challenges\, Cover Trees for nearest neighbor search\, Contextual Bandits (which he coined) for reinforcement learning applications\, and learning reductions. \n\nJohn is the author of the blog hunch.net and the principal developer of Vowpal Wabbit. He works at Microsoft Research New York\, of which he was one of the founding members\, and was previously affiliated with Yahoo! Research\, Toyota Technological Institute at Chicago\, and IBM’s Watson Research Center. He studied Physics and Computer Science at the California Institute of Technology\, earning a double bachelor’s degree in 1997\, and he received his Ph.D. in Computer Science from Carnegie Mellon University in the year of 2002. \n\nJohn was the program co-chair for the 2012 International Conference on Machine Learning (ICML)\, general chair for the 2016 ICML\, and is the President of ICML from 2019–2021.\n\n------\n\nPowered by addevent.com \nShare your next event with us!\n
X-ALT-DESC;FMTTYPE=text/html:FDS Seminar: “Discovering an Agent’s Configuration Space”
Speaker: John Langford
Microsoft Research New York
This is an in-person seminar.
Webcast
Abstract: Given potentially very rich and redundant sensory information which an agent receives, can the agent discover a configuration space summarizing all the configurations it can achieve in an environment? In 2-d free space this could be x,y,theta, but in environments with walls, movable objects, and other agents how can this be done? I’ll discuss a basic principle, theory, and experimental results suggesting this may be viable for _all_ agents with relatively few environment interactions.
Bio: John Langford is a computer scientist working in machine learning and learning theory, a field that he says “is shifting from an academic discipline to an industrial tool”.
He is well known for work on the Isomap embedding algorithm, CAPTCHA challenges, Cover Trees for nearest neighbor search, Contextual Bandits (which he coined) for reinforcement learning applications, and learning reductions.
John is the author of the blog hunch.net and the principal developer of Vowpal Wabbit. He works at Microsoft Research New York, of which he was one of the founding members, and was previously affiliated with Yahoo! Research, Toyota Technological Institute at Chicago, and IBM’s Watson Research Center. He studied Physics and Computer Science at the California Institute of Technology, earning a double bachelor’s degree in 1997, and he received his Ph.D. in Computer Science from Carnegie Mellon University in the year of 2002.
John was the program co-chair for the 2012 International Conference on Machine Learning (ICML), general chair for the 2016 ICML, and is the President of ICML from 2019–2021.
------
Powered by addevent.com
Share your next event with us!
LOCATION:DL220\, 10 Hillhouse Ave\, New Haven CT or Webcast: https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=1a9628bf-c5c4-4830-948b-af420136ee87
BEGIN:VALARM
TRIGGER:-PT30M
ACTION:DISPLAY
DESCRIPTION:Reminder
END:VALARM
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR