Skip to main content

Iterated Learning in Dynamic Social Networks

Author(s): Chazelle, Bernard; Wang, Chu

To refer to this page use:
Abstract: A classic finding by (Kalish et al., 2007) shows that no language can be learned iteratively by rational agents in a self-sustained manner. In other words, if A teaches a foreign language to B, who then teaches what she learned to C, and so on, the language will quickly get lost and agents will wind up teaching their own common native language. If so, how can linguistic novelty ever be sustained? We address this apparent paradox by considering the case of iterated learning in a social network: we show that by varying the lengths of the learning sessions over time or by keeping the networks dynamic, it is possible for iterated learning to endure forever with arbitrarily small loss.
Publication Date: 2019
Citation: Chazelle, Bernard, and Chu Wang. "Iterated Learning in Dynamic Social Networks." Journal of Machine Learning Research 20, no. 29 (2019): pp. 1-28.
ISSN: 1532-4435
EISSN: 1533-7928
Pages: 1 - 28
Type of Material: Journal Article
Journal/Proceeding Title: Journal of Machine Learning Research
Version: Final published version. This is an open access article.

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.