AI RESEARCH
Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference
arXiv CS.LG
•
ArXi:2604.20775v1 Announce Type: new Trajectory Inference (TI) seeks to recover latent dynamical processes from snapshot data, where only independent samples from time-indexed marginals are observed. In applications such as single-cell genomics, destructive measurements make path-space laws non-identifiable from finitely many marginals, leaving held-out marginal prediction as the dominant but limited evaluation protocol. We