Saved in:
Bibliographic Details
Main Authors: Shah, Nidhish, Mandal, Shaurjya, Azhar, Asfandyar
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.01443
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911562225156096
author Shah, Nidhish
Mandal, Shaurjya
Azhar, Asfandyar
author_facet Shah, Nidhish
Mandal, Shaurjya
Azhar, Asfandyar
contents When does consulting one information source raise the value of another, and when does it diminish it? We study this question for Bayesian decision-makers facing finite actions. The interaction decomposes into two opposing forces: a complement force, measuring how one source moves beliefs to where the other becomes more useful, and a substitute force, measuring how much the current decision is resolved. Their balance obeys a localization principle: substitution requires an observation to cross a decision boundary, though crossing alone does not guarantee it. Whenever posteriors remain inside the current decision region, the substitute force vanishes, and sources are guaranteed to complement each other, even when one source cannot, on its own, change the decision. The results hold for arbitrarily correlated sources and are formalized in Lean 4. Substitution is confined to the thin boundaries where decisions change. Everywhere else, information cooperates. Code and proofs: https://github.com/nidhishs/all-substitution-is-local.
format Preprint
id arxiv_https___arxiv_org_abs_2604_01443
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle All Substitution Is Local
Shah, Nidhish
Mandal, Shaurjya
Azhar, Asfandyar
Theoretical Economics
Artificial Intelligence
Information Theory
When does consulting one information source raise the value of another, and when does it diminish it? We study this question for Bayesian decision-makers facing finite actions. The interaction decomposes into two opposing forces: a complement force, measuring how one source moves beliefs to where the other becomes more useful, and a substitute force, measuring how much the current decision is resolved. Their balance obeys a localization principle: substitution requires an observation to cross a decision boundary, though crossing alone does not guarantee it. Whenever posteriors remain inside the current decision region, the substitute force vanishes, and sources are guaranteed to complement each other, even when one source cannot, on its own, change the decision. The results hold for arbitrarily correlated sources and are formalized in Lean 4. Substitution is confined to the thin boundaries where decisions change. Everywhere else, information cooperates. Code and proofs: https://github.com/nidhishs/all-substitution-is-local.
title All Substitution Is Local
topic Theoretical Economics
Artificial Intelligence
Information Theory
url https://arxiv.org/abs/2604.01443