Adaptive Inference through Bayesian and Inverse Bayesian Inference with Symmetry-Bias in Nonstationary Environments

TL;DR

This paper introduces a Bayesian and inverse Bayesian inference framework that incorporates symmetry bias to improve adaptability in nonstationary environments, balancing accuracy and responsiveness through dynamic learning rates and critical dynamics.

Contribution

It proposes the BIB inference framework that combines Bayesian and inverse Bayesian updates with symmetry bias, enabling rapid adaptation and criticality in changing environments.

Findings

BIB exhibits burst-like learning rate increases during environmental shifts.

BIB operates near a critical state, showing scale-free behavior.

It effectively balances adaptability and accuracy in nonstationary settings.

Abstract

This study proposes the novel Bayesian and inverse Bayesian (BIB) inference framework that incorporates symmetry bias into the Bayesian updating process to perform both conventional and inverse Bayesian updates concurrently. Conventional Bayesian inference is constrained by a fundamental trade-off between adaptability to abrupt environmental changes and accuracy during stable periods. The BIB framework addresses this limitation by dynamically modulating the learning rate via inverse Bayesian updates, thereby enhancing adaptive flexibility. The BIB model was evaluated in a sequential estimation task involving observations drawn from a Gaussian distribution with a stochastically time-varying mean, where it exhibited spontaneous bursts in the learning rate during environmental transitions, transiently entering high-sensitivity states that facilitated rapid adaptation. This burst-relaxation dynamic serves as a mechanism for balancing adaptability and accuracy. Furthermore, avalanche analysis, detrended fluctuation analysis, and power spectral analysis revealed that the BIB system likely operates near a critical state-a property not observed in standard Bayesian inference. This suggests that the BIB model uniquely achieves a coexistence of computational efficiency and critical dynamics, resolving the adaptability-accuracy trade-off while maintaining scale-free behavior. These findings offer a new computational perspective on scale-free dynamics in natural systems and provide valuable insights for the design of adaptive inference systems in nonstationary environments.