arXiv stat.ML
· Papers
Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking
arXiv:2608.03469v1 Announce Type: new Abstract: We study score learning for reflected diffusion on bounded domains. Reflection keeps trajectories feasible but does not ensure that the learned score satisfies the boundary behavior implied by the forward process. With implicit score matching, integration by parts leaves