2026-07-25T21:33:30Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:8171 2024-03-06T10:39:17Z ddc:004 open_access

Self-Sustaining Iterated Learning Chazelle, Bernard Wang, Chu Iterated learning language evolution iterated Bayesian linear regression non-equilibrium dynamics An important result from psycholinguistics (Griffiths & Kalish, 2005) states that no language can be learned iteratively by rational agents in a self-sustaining manner. We show how to modify the learning process slightly in order to achieve self-sustainability. Our work is in two parts. First, we characterize iterated learnability in geometric terms and show how a slight, steady increase in the lengths of the training sessions ensures self-sustainability for any discrete language class. In the second part, we tackle the nondiscrete case and investigate self-sustainability for iterated linear regression. We discuss the implications of our findings to issues of non-equilibrium dynamics in natural algorithms. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Bernard Chazelle and Chu Wang 2017 Is Part Of LIPIcs, Volume 67, 8th Innovations in Theoretical Computer Science Conference (ITCS 2017) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.ITCS.2017.17 urn:nbn:de:0030-drops-81711 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITCS.2017.17 eng https://creativecommons.org/licenses/by/3.0/legalcode