Iterated Belief Change as Learning

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.

Cite

Text

Schwind et al. "Iterated Belief Change as Learning." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/520

Markdown

[Schwind et al. "Iterated Belief Change as Learning." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/schwind2025ijcai-iterated/) doi:10.24963/IJCAI.2025/520

BibTeX

@inproceedings{schwind2025ijcai-iterated,
  title     = {{Iterated Belief Change as Learning}},
  author    = {Schwind, Nicolas and Inoue, Katsumi and Konieczny, Sébastien and Marquis, Pierre},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {4669-4677},
  doi       = {10.24963/IJCAI.2025/520},
  url       = {https://mlanthology.org/ijcai/2025/schwind2025ijcai-iterated/}
}