---
title: "Iterated Belief Change as Learning"
authors:
  - "Nicolas Schwind"
  - "Katsumi Inoue"
  - "Sébastien Konieczny"
  - "Pierre Marquis"
doi: "10.24963/ijcai.2025/520"
url: "https://ijcai.org/proceedings/2025/520"
pdf: "https://ijcai.org/proceedings/2025/0520.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "4669-4677"
track: "Main Track"
keywords:
  - "Knowledge Representation and Reasoning: KRR: Belief change"
  - "Knowledge Representation and Reasoning: KRR: Learning and reasoning"
---

# Iterated Belief Change as Learning

Nicolas Schwind, Katsumi Inoue, Sébastien Konieczny, Pierre Marquis

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 4669-4677. DOI: [10.24963/ijcai.2025/520](https://doi.org/10.24963/ijcai.2025/520)

## Abstract

In this work, we show how the class of improvement operators --- a general class of iterated belief change operators --- can be used to define a learning model. Focusing on binary classification, we present learning and inference algorithms suited to this learning model and we evaluate them empirically. Our findings highlight two key insights: first, that iterated belief change can be viewed as an effective form of online learning, and second, that the well-established axiomatic foundations of belief change operators offer a promising avenue for the axiomatic study of classification tasks.