Back to Upcoming Events
FDS Statistics & Data Science Seminar

S&DS Seminar: Stan Osher (UCLA), “Recent Results on Mean Field Games, Optimal Transport, and In-Context Learning”

Speaker: Stan Osher (UCLA)

Professor of Mathematics & Computer Science, Electrical Engineering & Chemical and Biomolecular Engineering, University of California, Los Angeles
Director of Special Projects, Institute for Pure and Applied Mathematics (IPAM)

University of California, Los Angeles

Monday, November 18, 2024

4:00PM - 5:00PM

4:00PM - 5:00PM

Location: Yale Institute for Foundations of Data Science, Kline Tower 13th Floor, Room 1327, New Haven, CT 06511 and via Webcast: https://yale.zoom.us/j/94223816617

Add To: Google Calendar | Outlook | iCal File

Abstract: We have recently been developing algorithms related to mean field games, optimal transport,  in-context learning, score based generative models and links between Laplace’s method, the Moreau envelope and Hamilton-Jacobi equations. I will try to give a coherent talk including many of these.

Speaker bio: Stanley Osher, Professor at the University of California, Los Angeles, serves as the Director of Special Projects within the Institute for Pure and Applied Mathematics.

He has invented innovative numerical technologies and has applied them to nearly all fields of numerical simulation, from aeronautics to material science and from brain science to the movie industry.

Among his inventions, three have become universal: the level set method, the ENO and WENO schemes and the total variation. For instance, the joint key words “level set” and “method” find more than one million hits on Google and they are all about the Osher-Sethian surface evolution method.

Submit an Event

Interested in creating your own event, or have an event to share? Please fill the form if you’d like to send us an event you’d like to have added to the calendar.

Submit an Event

Share your event ideas with us using the form below.

"*" indicates required fields

MM slash DD slash YYYY
Start Time*
:
End Time*
: