How does training shape the Riemannian geometry of neural network representations?

An official website of the United States government Here's how you know

Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

This content will become publicly available on September 22, 2026

How does training shape the Riemannian geometry of neural network representations?

Author(s) / Creator(s):: Zavatone-Veth, JA; Yang, S; Rubinfien, J A; Pehlevan, C

Publisher / Repository:: NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations