[Sds-seminars] Today: Robert Schapire (Microsoft Research) “Convex Analysis at Infinity: An Introduction to Astral Space”

[Hau, Emily]

[Graphical user interface, text, application  Description automatically generated]

FDS Colloquium: “Convex Analysis at Infinity: An Introduction to Astral Space”



Speaker: Robert Schapire
Computer Scientist,
Microsoft Research (NYC Lab)


Monday, April 24, 2023
   3:30pm – Pre-talk meet and greet teatime – Dana House, 24 Hillhouse Avenue
    4:00pm – 5:00pm Mason Lab 211, 9 Hillhouse Ave or virtual<https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=e1a54b37-2829-4b7a-841e-af93011fd666>

Add To: Google Calendar<https://calendar.google.com/calendar/r/eventedit?text=FDS+Colloquium%3A+Robert+Schapire+%28Microsoft+Research%29+%26%238220%3BConvex+Analysis+at+Infinity%3A+An+Introduction+to+Astral+Space%26%238221%3B&details=Speaker%3A+Robert+SchapireComputer+Scientist%2CMicrosoft+Research+%28NYC+Lab%29+Hosted+by%3A+Dan+Spielman+In+person+event+with+remote+access+via+Panopto.+Abstract%3A+Not+all+convex+functions+have+finite+minimizers%3B+some+can+only+be+minimized+by+a+sequence+as+it+heads+to+infinity.%26nbsp%3B+In+this+work%2C+we+aim+to+develop+a+theory+for+understanding+such+minimizers+at+infinity.%26nbsp%3B%26hellip%3B+%3Ca+class%3D%22continue%22+href%3D%22https%3A%2F%2Ffds.yale.edu%2Fcalendar_event%2Ffds-colloquium-schapire%2F%22%3Econtinue+reading%3Cspan%3E+FDS+Colloquium%3A+Robert+Schapire+%28Microsoft+Research%29+%26%238220%3BConvex+Analysis+at+Infinity%3A+An+Introduction+to+Astral+Space%26%238221%3B%3C%2Fspan%3E%3C%2Fa%3E...&location=Mason+Lab+211+with+remote+access+option%2C+9+Hillhouse+Avenue%2C+New+Haven%2C+CT+06520&dates=20230424T200000Z/20230424T210000Z> | Outlook<https://fds.yale.edu/wp-admin/admin-ajax.php?event=1024&action=download_ical_file> | iCal File<https://fds.yale.edu/wp-admin/admin-ajax.php?event=1024&action=download_ical_file>


Abstract: Not all convex functions have finite minimizers; some can only be minimized by a sequence as it heads to infinity.  In this work, we aim to develop a theory for understanding such minimizers at infinity.  We study astral space, a compact extension of Euclidean space to which such points at infinity have been added.  Astral space is constructed to be as small as possible while still ensuring that all linear functions can be continuously extended to the new space.  Although not a vector space, nor even a metric space, astral space is nevertheless so well-structured as to allow useful and meaningful extensions of such concepts as convexity, conjugacy, and subdifferentials.  We develop these concepts and analyze various properties of convex functions on astral space, including the detailed structure of their minimizers, exact characterizations of continuity, and convergence of descent algorithms.



This is joint work with Miroslav Dudík and Matus Telgarsky.



Bio: Robert Schapire is a Partner Researcher at Microsoft Research in New York City. He received his PhD from MIT in 1991. After a short postdoc at Harvard, he joined the technical staff at AT&T Labs (formerly AT&T Bell Laboratories) in 1991. In 2002, he became a Professor of Computer Science at Princeton University. He joined Microsoft Research in 2014. His awards include the 1991 ACM Doctoral Dissertation Award, the 2003 Gödel Prize, and the 2004 Kanelakkis Theory and Practice Award (both of the last two with Yoav Freund). He is a fellow of the AAAI, and a member of both the National Academy of Engineering and the National Academy of Sciences. His main research interest is in theoretical and applied machine learning. Website: http://rob.schapire.net/



Hosted by: Dan Spielman


Upcoming:

May 1: Workshop: Healthcare Data Science (registration required)<https://fds.yale.edu/calendar_event/data-science-for-healthcare/>

May 3: FDS Seminar, Wei Ji Ma<https://fds.yale.edu/calendar_event/fds-seminar-weiji-ma/>


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<mailto:emily.hau at yale.edu> | P: 203-436-4732
@yaledatascience @YINSedge @EmilyDeeganHau

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20230424/07a1e7f8/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 20707 bytes
Desc: image001.png
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20230424/07a1e7f8/attachment.png>