Preprint
Aug 2026
Finite-Sample Metric Non-Collapse for Geometrically Supervised Latent World Models in Control
A finite-sample learning-to-control theory for geometrically supervised latent models of nonlinear deterministic systems is established and an encoder-only local--global metric hinge is introduced that enforces directional resolution and separated-state discrimination.
Alain Bensoussan, M. Phung, Minh-Binh Tran
· 0 citations