Continual Learning as Shared-Manifold Continuation Under Compatible Shift

ArXi:2603.20036v1 Announce Type: new Continual learning methods usually preserve old behavior by regularizing parameters, matching old outputs, or replaying previous examples. These strategies can reduce forgetting, but they do not directly specify how the latent representation should evolve. We study a narrower geometric alternative for the regime where old and new data should remain on the same latent: continual learning as continuation of a shared manifold.