SEP 10, 2026 · PREPRINT
How Wrong Can a Good Predictor Be? Diverging Updates with Vanishing Predictive KL
arXiv
A theoretical analysis proving a counterintuitive mathematical property in a specific model class, without empirical validation or clinical application.
Reported
Update map separation growth rateat least linear in L_K(q)
Terminal KL convergenceH(q)=⌈−log(q)/c⌉+1
State dimensionsK−1 belief coordinates