[Theory] [Theory Lunch] Ryan Robinett (U. of Chicago), Wednesday 2/2, 12:30pm-1:30pm, JCL 390.

Antares Chen antaresc at uchicago.edu
Mon Jan 31 08:00:00 CST 2022


************************************************************
**************************

*Date:* February 2, Wednesday
*Time: *12:30pm CT
*Location: *JCL 390

*Speaker:  Ryan Robinett (University of Chicago)*

*Title: **A Data Structure for High-dimensional Manifold Representation
Amenable to Riemannian Optimization*

*Zoom: *[link
<https://uchicago.zoom.us/j/92270537164?pwd=cXRxaWl2QXhWZjFBU29TbVorYy84dz09>
]

*Abstract:* The field of Riemannian Optimization generalizes optimization
techniques from Euclidean state-spaces to Riemannian manifolds. While the
theory of Riemannian optimization is well developed, it is scarcely
implemented due to “update-and-project” methods on representations of
Riemannian manifolds within a higher-dimensional Euclidean space being
costly. Conjugately, while dimensionality reduction techniques allow for
insightful, simplifying looks into high-dimensional data, only linear
dimensionality reduction techniques succeed in preserving metric
information to a degree necessary to perform Riemannian optimization on the
reduced space. In this talk, we demonstrate a data structure which allows
the user to implement Riemannian optimization algorithms on a
pseudo-Riemannian simplicial complex which closely approximates a manifold
learned from point cloud data.

*Note*: In line with current departmental guidance, lunch will not be
served at the talk.

[Theory Lunch Webpage <https://orecchia.net/event/theory-lunch/>]
[Theory Lunch Calendar
<https://calendar.google.com/calendar/u/0/embed?src=c_osgf1c1qemdras8mu7l7pdhjrs@group.calendar.google.com&ctz=America/Chicago>
]

************************************************************
**************************
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20220131/174c1fe1/attachment-0001.html>


More information about the Theory mailing list