[Sds-seminars] [Sds-announce] Fwd: [FDS] 12/7: John Langford (Microsoft Research New York)

Mon Dec 5 14:21:03 EST 2022

---------- Forwarded message ---------
From: Hau, Emily <emily.hau at yale.edu>
Date: Mon, Dec 5, 2022 at 12:46 PM
Subject: [FDS] 12/7: John Langford (Microsoft Research New York)
To: fds-announce at mailman.yale.edu <fds-announce at mailman.yale.edu>,
yins at mailman.yale.edu <yins at mailman.yale.edu>

[image: FDS Seminars header]

*Wednesday, December 7, 2022 - 4:00pm *

*FDS Seminar  “Discovering an Agent’s Configuration Space”  *

*Speaker: John Langford*
Microsoft Research New York

*Location:*  DL220, 10 Hillhouse Avenue New Haven, CT or Webcast
<https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=1a9628bf-c5c4-4830-948b-af420136ee87>

*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.

*Speaker 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.

Website: https://hunch.net/~jl/

*Add event to calendar*

*[image: Apple]* <https://www.addevent.com/event/WF15489917+apple> *[image:
Google]* <https://www.addevent.com/event/WF15489917+google> *[image: Office
365]* <https://www.addevent.com/event/WF15489917+office365> *[image:
Outlook]* <https://www.addevent.com/event/WF15489917+outlook> *[image:
Outlook.com]* <https://www.addevent.com/event/WF15489917+outlookcom> *[image:
Yahoo]* <https://www.addevent.com/event/WF15489917+yahoo>

*Thursday, December 8, 2022 – 7:00pm*

*The Jackson School of Global Affairs will host the discussion, “Artificial
Intelligence and Diplomacy.”  *

Speakers include Defense Advanced Research Projects Agency (DARPA) Program
Manager Tejas Patel, and Ambassador David Robinson, moderated by Jackson
lecturer Casey King.

*Location:* Horchow Hall 103 (GM Room) 55 Hillhouse Avenue New Haven CT
06511

Patel is DARPA’s Program Manager for SHADE: an AI research initiative using
diplomacy to better understand the nuance of communication intent behind
actions.  Robinson is a retired U.S. diplomat whose previous roles include
the Principal Deputy High Representative in Bosnia and Herzegovina, where
he was responsible for implementing the Dayton Peace Agreement. Prior to
that, he was the Assistant Chief of Mission at the United States Embassy in
Kabul, Afghanistan from 2013 to 2014, the Principal Deputy Assistant
Secretary of State and the Deputy Assistant Secretary of State in the
Bureau of Population, Refugees and Migration from 2009 to 2013, and the
Special Coordinator for Venezuela in the Bureau of Western Hemisphere
Affairs from 2008 to 2009.

The panel will be moderated by Casey King, a 2021 DARPA AI Exploration
Award Recipient and a Jackson School faculty member who teaches stats and
data science.  The event is open to the Yale campus community (Faculty,
Graduate and Professional, Staff, Students, Undergraduate, Yale
Postdoctoral Trainees).
https://jackson.yale.edu/jackson-events/artificial-intelligence-and-diplomacy/

*Add event to calendar*

*[image: Apple]* <https://www.addevent.com/event/Mv15695020+apple> *[image:
Google]* <https://www.addevent.com/event/Mv15695020+google> *[image: Office
365]* <https://www.addevent.com/event/Mv15695020+office365> *[image:
Outlook]* <https://www.addevent.com/event/Mv15695020+outlook> *[image:
Outlook.com]* <https://www.addevent.com/event/Mv15695020+outlookcom> *[image:
Yahoo]* <https://www.addevent.com/event/Mv15695020+yahoo>

*Upcoming:*

12/13 at 2pm: Data Science Project Match <http://evt.to/aiihaadow>

12/14 at 4pm: FDS Seminar, Robert Schapire <http://evt.to/aiusmoeaw>
(Microsoft Research New York), “Convex Analysis at Infinity: An
Introduction to Astral Space”

Emily E. H. Hau | Associate Director, Data Science @ Yale University

*Yale Institute for Foundations of Data Science (FDS)*

*Yale Institute for Network Science (YINS)*

17 Hillhouse Avenue | Room 341 | New Haven, CT 06511

*emily.hau at yale.edu <emily.hau at yale.edu> | *P: 203-436-4732

@yaledatascience @YINSedge @EmilyDeeganHau

-- 
Fds-announce mailing list
Fds-announce at mailman.yale.edu
https://mailman.yale.edu/mailman/listinfo/fds-announce
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221205/3b2e587b/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 736 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221205/3b2e587b/attachment.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.png
Type: image/png
Size: 1073 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221205/3b2e587b/attachment-0001.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image003.png
Type: image/png
Size: 769 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221205/3b2e587b/attachment-0002.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image004.png
Type: image/png
Size: 614 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221205/3b2e587b/attachment-0003.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image005.png
Type: image/png
Size: 599 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221205/3b2e587b/attachment-0004.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image006.png
Type: image/png
Size: 642 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221205/3b2e587b/attachment-0005.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image007.png
Type: image/png
Size: 24128 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221205/3b2e587b/attachment-0006.png>
-------------- next part --------------
-- 
Sds-announce mailing list
Sds-announce at mailman.yale.edu
https://mailman.yale.edu/mailman/listinfo/sds-announce