Events
FDS Colloquium
Co-discovering graphical structure and functional relationships within data: A Gaussian Process framework for connecting the dots
 |
Speaker: Houman Owhadi (Caltech) Professor of Applied and Computational Mathematics and Control and Dynamical Systems California Institute of Technology Wednesday, October 30, 2024 11:30AM - 1:30PM 11:30am: Lunch in room 1307
12:00pm: Talk in 1327 Location: Yale Institute for Foundations of Data Science, Kline Tower 13th Floor, Room 1327, New Haven, CT 06511 and via Webcast: https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=9e9b71f5-9d53-4242-b7a7-b21000ee47e6 |
Abstract: Most scientific challenges can be framed into one of the following three levels of complexity of function approximation.
- Type 1: Approximate an unknown function given input/output data.
- Type 2: Consider a collection of variables and functions, some of which are unknown, indexed by the nodes and hyperedges of a hypergraph (a generalized graph where edges can connect more than two vertices). Given partial observations of the variables of the hypergraph (satisfying the functional dependencies imposed by its structure), approximate all the unobserved variables and unknown functions.
- Type 3: Expanding on Type 2, if the hypergraph structure itself is unknown, use partial observations of the variables of the hypergraph to discover its structure and approximate its unknown functions.
Examples of Type 2 problems include solving and learning (possibly stochastic) nonlinear partial differential equations (PDEs), while Type 3 problems encompass learning dependencies between variables in a mechanical system, identifying chemical reaction networks, and determining relationships between genes through a protein-signaling network. Although Gaussian Process (GP) methods are sometimes perceived as a well-founded but old technology limited to Type 1 curve fitting, they can be generalized to an interpretable framework for solving Type 2 and Type 3 problems, all while maintaining the simple and transparent theoretical and computational guarantees of kernel/optimal recovery methods.
Bio: Professor Owhadi’s research concerns the exploration of interplays between numerical approximation, statistical inference and learning from a game theoretic perspective. Whereas the process of discovery is usually based on a combination of trial and error, insight and plain guesswork, his research is motivated by the facilitation/automation possibilities emerging from these interplays.
Website: https://www.cms.caltech.edu/people/owhadi
Add To: Google Calendar | Outlook | iCal File
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.