Cognitive Flexibility as a Latent Structural Operator for Bayesian State Estimation

TL;DR

This paper introduces Cognitive Flexibility, a novel operator for Bayesian state estimation that adaptively selects latent structures online, improving predictive accuracy in mismatched models while maintaining standard filtering when correct.

Contribution

It formalizes structural mismatch as predictive inconsistency and proposes a belief-structure recursion with finite switching capabilities for better model adaptation.

Findings

CF improves predictive accuracy under model mismatch.

CF remains non-intrusive when the model is correctly specified.

The belief-structure recursion is well posed and exhibits a structural descent property.

Abstract

Deep stochastic state-space models enable Bayesian filtering in nonlinear, partially observed systems but typically assume a fixed latent structure. When this assumption is violated, parameter adaptation alone may result in persistent belief inconsistency. We introduce \emph{Cognitive Flexibility} (CF) as a representation-level operator that selects latent structures online via an innovation-based predictive score, while preserving the Bayesian filtering recursion. Structural mismatch is formalized as irreducible predictive inconsistency under fixed structure. The resulting belief--structure recursion is shown to be well posed, to exhibit a structural descent property, and to admit finite switching, with reduction to standard Bayesian filtering under correct specification. Experiments on latent-dynamics mismatch, observation-structure shifts, and well-specified regimes confirm that CF improves predictive accuracy under a mismatch while remaining non-intrusive when the model is correctly specified.