Saved in:
Bibliographic Details
Main Authors: Baković, Luka, Como, Giacomo, Fagnani, Fabio, Proskurnikov, Anton, Tegling, Emma
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.11808
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912587613995008
author Baković, Luka
Como, Giacomo
Fagnani, Fabio
Proskurnikov, Anton
Tegling, Emma
author_facet Baković, Luka
Como, Giacomo
Fagnani, Fabio
Proskurnikov, Anton
Tegling, Emma
contents Motivated by the well established idea that collective wisdom is greater than that of an individual, we propose a novel learning dynamics as a sort of companion to the Abelson model of opinion dynamics. Agents are assumed to make independent guesses about the true state of the world after which they engage in opinion exchange leading to consensus. We investigate the problem of finding the optimal parameters for this exchange, e.g. those that minimize the variance of the consensus value. Specifically, the parameter we examine is susceptibility to opinion change. We propose a dynamics for distributed learning of the optimal parameters and analytically show that it converges for all relevant initial conditions by linking to well established results from consensus theory. Lastly, a numerical example provides intuition on both system behavior and our proof methods.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11808
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continuous-Time Distributed Learning for Collective Wisdom Maximization
Baković, Luka
Como, Giacomo
Fagnani, Fabio
Proskurnikov, Anton
Tegling, Emma
Systems and Control
93-10
Motivated by the well established idea that collective wisdom is greater than that of an individual, we propose a novel learning dynamics as a sort of companion to the Abelson model of opinion dynamics. Agents are assumed to make independent guesses about the true state of the world after which they engage in opinion exchange leading to consensus. We investigate the problem of finding the optimal parameters for this exchange, e.g. those that minimize the variance of the consensus value. Specifically, the parameter we examine is susceptibility to opinion change. We propose a dynamics for distributed learning of the optimal parameters and analytically show that it converges for all relevant initial conditions by linking to well established results from consensus theory. Lastly, a numerical example provides intuition on both system behavior and our proof methods.
title Continuous-Time Distributed Learning for Collective Wisdom Maximization
topic Systems and Control
93-10
url https://arxiv.org/abs/2509.11808