Rational v. Radical: Trajectory Properties of Iterated Bayesian Updates

Iterating Jeffrey's update on fixed evidence gives a maximum-likelihood estimate under suitable support conditions. What is less clear would be how the trajectories are organized, and what happens when we trace them in reverse. For a fixed strictly positive, invertible classical channel and full-support evidence, reverse iteration corresponds to repeated prior hacking. Almost every interior prior then approaches certainty in one possibility while each nontrivial step worsens agreement with the evidence. We call this limiting behavior radicalization. Priors that approach the same pure state form a Bayes phase. In the phase diagrams, the separating trajectories instead approach facet fixed points determined by M-projections. We also ask whether one can choose evidence that brings every interior prior to the same conclusion. For a strictly positive, invertible channel this is always possible, although one cannot always prescribe which conclusion it will be

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.24430
Primary Topic
Bayesian Modeling and Causal Inference
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Rational v. Radical: Trajectory Properties of Iterated Bayesian Updates

Peter Sidajaya, Clive Cenxin Aw, Lynette Zhong Ling Wang
arXiv (Cornell University)
Bayesian Modeling and Causal Inference
preprint

Rational v. Radical: Trajectory Properties of Iterated Bayesian Updates

Peter Sidajaya, Clive Cenxin Aw, Lynette Zhong Ling Wang
preprint en

Abstract

Iterating Jeffrey's update on fixed evidence gives a maximum-likelihood estimate under suitable support conditions. What is less clear would be how the trajectories are organized, and what happens when we trace them in reverse. For a fixed strictly positive, invertible classical channel and full-support evidence, reverse iteration corresponds to repeated prior hacking. Almost every interior prior then approaches certainty in one possibility while each nontrivial step worsens agreement with the evidence. We call this limiting behavior radicalization. Priors that approach the same pure state form a Bayes phase. In the phase diagrams, the separating trajectories instead approach facet fixed points determined by M-projections. We also ask whether one can choose evidence that brings every interior prior to the same conclusion. For a strictly positive, invertible channel this is always possible, although one cannot always prescribe which conclusion it will be

arXiv (Cornell University)
Bayesian Modeling and Causal Inference
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon