Skip to yearly menu bar Skip to main content


Workshop

Geometry-grounded Representation Learning and Generative Modeling

Sharvaree Vadgama 路 Erik Bekkers 路 Alison Pouplin 路 Robin Walters 路 Hannah Lawrence 路 S茅kou-Oumar Kaba 路 Jakub Tomczak 路 Tegan Emerson 路 Henry Kvinge 路 Stefanie Jegelka

Schubert 1 - 3

Sat 27 Jul, midnight PDT

By recognizing that nearly all data is rooted in our physical world, and thus inherently grounded in geometry and physics, it becomes evident that learning systems should preserve this grounding throughout the process of representation learning in order to be meaningful. For example, preserving group transformation laws and symmetries through equivariant layers is crucial in domains such as computational physics, chemistry, robotics, and medical imaging. It leads to effective and generalizable architectures and improved data efficiency. Similarly, in generative models applied to non-Euclidean data spaces, maintaining the manifold structure is essential to obtain meaningful samples. Therefore, this workshop focuses on the principle of grounding in geometry, which we define as follows: A representation, method, or theory is grounded in geometry if it can be amenable to geometric reasoning, that is, it abides by the mathematics of geometry.

Chat is not available.
Timezone: America/Los_Angeles

Schedule