[Sds-seminars] 4/20 FDS Colloquium: Philippe Rigollet (MIT) “Statistical applications of Wasserstein gradient flows”

[Hau, Emily]

[Graphical user interface, text, application  Description automatically generated]
“Statistical applications of Wasserstein gradient flows”

Speaker: Philippe Rigollet, PhD
Professor of Mathematics
Massachusetts Institute of Technology

Thursday, April 20, 2023, 4:00 – 5:00 pm

Add To: Google Calendar<https://calendar.google.com/calendar/r/eventedit?text=FDS+Colloquium%3A+Philippe+Rigollet+%28MIT%29+%26%238220%3BStatistical+applications+of+Wasserstein+gradient+flows%26%238221%3B&details=Speaker%3A+Philippe%26nbsp%3BRigollet%2C+PhDProfessor+of+MathematicsMassachusetts+Institute+of+Technology+Hosted+by+Yihong+Wu+In-person+event+with+remote+access+option+via%26nbsp%3BPanopto+Statistical+applications+of+Wasserstein+gradient+flows+Abstract%3A+Otto+calculus+is+a+fundamental+toolbox+in+mathematical+optimal+transport%2C+imparting+the+Wasserstein+space+of+probability+measures+with+a+Riemmanian+structure.+In+particular%2C+one+can+compute+the+Riemannian+gradient%26hellip%3B+%3Ca+class%3D%22continue%22+href%3D%22https%3A%2F%2Ffds.yale.edu%2Fcalendar_event%2Ffds-seminar-phillipe-rigollet%2F%22%3Econtinue+reading%3Cspan%3E+FDS+Colloquium%3A+Philippe+Rigollet+%28MIT%29+%26%238220%3BStatistical+applications+of+Wasserstein+gradient+flows%26%238221%3B%3C%2Fspan%3E%3C%2Fa%3E...&location=17+Hillhouse+Ave%2C+3rd+floor%2C+17+Hillhouse+Avenue%2C+3rd+floor%2C+New+Haven%2C+CT+06519&dates=20230420T200000Z/20230420T210000Z> | Outlook<https://fds.yale.edu/wp-admin/admin-ajax.php?event=1074&action=download_ical_file> | iCal File<https://fds.yale.edu/wp-admin/admin-ajax.php?event=1074&action=download_ical_file>

This in-person seminar will be held at 17 Hillhouse, 3rd Floor Common Area with remote access option via Panopto<https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=c592e4df-1bdf-4360-b6d8-af93011fd624>

Abstract: Otto calculus is a fundamental toolbox in mathematical optimal transport, imparting the Wasserstein space of probability measures with a Riemmanian structure. In particular, one can compute the Riemannian gradient of a functional over this space and, in turn, optimize it using Wasserstein gradient flows. The necessary background to define and compute Wasserstein gradient flows will be presented in the first part of the talk before moving to several statistical applications ranging from variational inference to maximum likelihood estimation in Gaussian mixture models. Emphasis will be placed on conceptual ideas in order for the talk to be accessible to a broad audience.

Bio: Philippe Rigollet works at the intersection of statistics, machine learning, and optimization, focusing primarily on the design and analysis of statistical methods for high-dimensional problems. His recent research focuses on statistical optimal transport and its applications to geometric data analysis and sampling. Website: www-math.mit.edu/~rigollet<http://www-math.mit.edu/~rigollet>

Hosted by Yihong Wu

Upcoming:

FDS Colloquium: Robert Schapire (Microsoft Research) “Convex Analysis at Infinity: An Introduction to Astral Space”<https://fds.yale.edu/calendar_event/fds-colloquium-schapire/>
April 24, 2023 at 4:00 pm

Workshop: Healthcare Data Science<https://fds.yale.edu/calendar_event/data-science-for-healthcare/>
May 1, 2023 at 8:00 am

FDS Seminar: Weiji Ma<https://fds.yale.edu/calendar_event/fds-seminar-weiji-ma/>
May 3, 2023 at 4:00 pm



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/20230418/31fb4742/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 21605 bytes
Desc: image001.png
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20230418/31fb4742/attachment.png>