2606.10596v1 Jun 09, 2026 cs.LG

Embedding Hybrid Systems into Continuous Latent Vector Fields

K. Sreenath
K. Sreenath
Citations: 13,589
h-index: 55
Sangli Teng
Sangli Teng
Citations: 686
h-index: 11
Hang Liu
Hang Liu
Citations: 11
h-index: 2

This work proves that an $n$-dimensional hybrid system can be embedded into an $m$-dimensional Euclidean space equipped with a continuous vector field on its embedded image whenever $m>2n$. This result suggests that an intrinsically discontinuous hybrid system generically admits a continuous extrinsic representation that is well-posed for differentiable optimization. Building on this existence theorem, we show that a latent Neural ODE with consistency loss in both the latent and state space can accurately recover the flow of hybrid systems. Extensive experiments suggest the proposed method outperforms the existing method in learning hybrid systems with varying geometries from only time series data.

0 Citations
0 Influential
27.5 Altmetric
137.5 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!