A method using convex autoencoders and kernel-based learning creates a finite abstraction in latent space that overapproximates unknown dynamical systems, enabling scalable verification with correctness guarantees that transfer back to the original system.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Verification of Unknown Dynamical Systems via Autoencoder Latent Space
A method using convex autoencoders and kernel-based learning creates a finite abstraction in latent space that overapproximates unknown dynamical systems, enabling scalable verification with correctness guarantees that transfer back to the original system.