Self-Sustaining Iterated Learning
This addresses a foundational issue in language learning and natural algorithms, with potential implications for non-equilibrium dynamics, though it appears incremental as it builds on existing results.
The paper tackles the problem that no language can be learned iteratively by rational agents in a self-sustaining manner, as shown in prior work, and modifies the learning process to achieve self-sustainability by increasing training session lengths for discrete language classes and investigating it for iterated linear regression.
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.