[Colloquium] TODAY 2PM: Data Science/CS Candidate Talk - Haifeng Xu (U. of Virginia)

[Rob Mitchum]

*Data Science Institute/Computer Science Candidate Seminar*

*Haifeng Xu*
*Assistant Professor*
*University of Virginia*

*Tuesday, March 8th*
*2:00 p.m. - 3:00 p.m.*
*In Person: John Crerar Library, Room 390*
*Remote: Live Stream <http://live.cs.uchicago.edu/haifengxu/> or Zoom
<https://uchicago.zoom.us/j/99751674951?pwd=SHo3ajM3Z0xEbHBNR2xhSUd4dGVQQT09>
(details
below)*


*The Interplay of Learning and Game Theory in the Information Age*
Strategic interactions among self-interested agents (a.k.a., games) are
ubiquitous, ranging from economic activity in the Internet to
defender-adversary interactions in national security. Agents' different
access to diverse information sources in this digital age gives rise to a
fundamental challenge in game theory, i.e., reasoning under agents'
asymmetric knowledge regarding their environment as well as the preferences
and actions of others. In this talk, I will describe my research on
leveraging computational approaches to tackle this new and timely
challenge. In particularly, I will illustrate the interesting interplay
between machine learning and game theory through two complementary threads
of my research: (1)  the learning-theoretic study of foundational game
models, which not only reveals new insights about the solution of these
models but also makes them applicable to settings with uncommon knowledge;
(2) the game-theoretic study of basic machine learning problems (i.e.,
classification), which not only makes classification applicably to complex
strategic settings but also results in a generalized theory of PAC
learnability. Finally, I will mention how these studies and the future plan
may lead to my long-term goal of designing principled AI agents that can
intelligently learn and act in informationally complex settings.

*Bio*: Haifeng Xu <https://www.haifeng-xu.com/> is an assistant professor
in Computer Science at the University of Virginia. His research interests
include artificial intelligence, computational game theory, algorithms, and
machine learning. He studies decision making and learning in multi-agent
environments, particularly in informationally complex setups (e.g., with
asymmetric or limited access to information/data). Prior to UVA, Haifeng
was a postdoc at Harvard and obtained his PhD in Computer Science from the
University of Southern California. His research has been recognized by
multiple awards, including a Google Faculty Research Award, honorable
mention for the ACM SIGecom Dissertation Award, runner-up for the IFAAMAS
Victor Lesser Distinguished Dissertation Award, a Google PhD fellowship,
and multiple best paper awards.

*Host*: Raul Castro Fernandez

*Zoom Info:*
https://uchicago.zoom.us/j/99751674951?pwd=SHo3ajM3Z0xEbHBNR2xhSUd4dGVQQT09
Meeting ID: 997 5167 4951
Password: ds2022




-- 
*Rob Mitchum*

*Associate Director of Communications for Data Science and Computing*
*University of Chicago*
*rmitchum at uchicago.edu <rmitchum at ci.uchicago.edu>*
*773-484-9890*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20220308/f078f53e/attachment.html>