Singular Equilibrium and Selection of Narratives
Abstract
An agent learns from data that many parameters of her model explain equally well. Berk's theorem states that her belief concentrates on the parameters that best fit the data, but does not select between them. We show that, with a continuum of parameters, the posterior concentrates on the best-fitting parameters with the smallest local learning coefficient. We propose a definition of narratives, subsets of the best-fitting parameters on which the learning coefficient is constant. Narratives are characterized by the number of coincidences they require (complexity) and how exactly each must hold (robustness). When the agent's actions affect her data, every long-run action is a singular equilibrium, a best reply to a belief supported on the least complex and most robust narratives. Singular equilibrium refines Berk-Nash and self-confirming equilibrium by restricting overly complex or knife-edge off-path beliefs, and its strict uniform version characterizes uniformly stable actions.
Related
- Equilibrium Singular Dividend Control with Regime Switching and Bankruptcy under Non-Exponential Discounting
- Immersed Boundary Electrodiffusion in the Wasserstein Gradient Flow Formalism: Global Well-Posedness, Non-Equilibrium Thermodynamics, and Singular Asymptotics
- Finite inverse nodal problems for singular weighted Sturm--Liouville equations: variational selection and spectral matching
- Mutation--selection balance on an infinite trait space: confinement, drift and equilibrium
- Time-Varying Data as Sheaves: an Invitation to Narratives
BibTeX
@misc{jin2026singular,
title = {{Singular Equilibrium and Selection of Narratives}},
author = {David J. Jin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.11615},
eprint = {2610.11615},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.11615},
}
RIS
TY - UNPB
TI - Singular Equilibrium and Selection of Narratives
AU - David J. Jin
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2610.11615
UR - https://arxiv.org/abs/2610.11615
AB - An agent learns from data that many parameters of her model explain equally well. Berk's theorem states that her belief concentrates on the parameters that best fit the data, but does not select between them. We show that, with a continuum of parameters, the posterior concentrates on the best-fitting parameters with the smallest local learning coefficient. We propose a definition of narratives, subsets of the best-fitting parameters on which the learning coefficient is constant. Narratives are characterized by the number of coincidences they require (complexity) and how exactly each must hold (robustness). When the agent's actions affect her data, every long-run action is a singular equilibrium, a best reply to a belief supported on the least complex and most robust narratives. Singular equilibrium refines Berk-Nash and self-confirming equilibrium by restricting overly complex or knife-edge off-path beliefs, and its strict uniform version characterizes uniformly stable actions.
ER -