SOURCE-LINKED INTELLIGENCE

How Wrong Can a Good Predictor Be? Diverging Updates with Vanishing Predictive KL

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Accurate posterior prediction need not require accurate approximation of Bayesian updates. We prove that an unbounded gap between the update maps can coexist with vanishing predictive KL for every fixed finite $K\ge2$ in a stationary symmetric Gaussian HMM. Exact Bayesian mixing and an explicit deterministic radial filter act on the same $K-1$ belief coordinates. As $q\to0^+$, their separation in centered logits in the worst case grows at least linearly in the natural confidence scale $L_K(q)$, while their categorical $D_{\mathrm{KL}}(\mathrm{exact}\|\mathrm{radial})$ vanishes at the same expl

Read original source ↗ Open in workspace

recordType

paper

region

Global