Autoencoding Dynamics: Topological Limitations and Capabilities
Kvalheim, Matthew D., Sontag, Eduardo D.
–arXiv.org Artificial Intelligence
Given a "data manifold" $M\subset \mathbb{R}^n$ and "latent space" $\mathbb{R}^\ell$, an autoencoder is a pair of continuous maps consisting of an "encoder" $E\colon \mathbb{R}^n\to \mathbb{R}^\ell$ and "decoder" $D\colon \mathbb{R}^\ell\to \mathbb{R}^n$ such that the "round trip" map $D\circ E$ is as close as possible to the identity map $\mbox{id}_M$ on $M$. We present various topological limitations and capabilites inherent to the search for an autoencoder, and describe capabilities for autoencoding dynamical systems having $M$ as an invariant manifold.
arXiv.org Artificial Intelligence
Nov-12-2025
- Country:
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America > United States
- Maryland
- Baltimore (0.04)
- Baltimore County (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- Rhode Island > Providence County
- Providence (0.04)
- Maryland
- Europe > United Kingdom
- Genre:
- Research Report (0.50)
- Technology: