Overabundant Information and Learning Traps
Computer Science and Game Theory
2018-06-20 v2 Machine Learning
Abstract
We develop a model of social learning from overabundant information: Short-lived agents sequentially choose from a large set of (flexibly correlated) information sources for prediction of an unknown state. Signal realizations are public. We demonstrate two starkly different long-run outcomes: (1) efficient information aggregation, where the community eventually learns as fast as possible; (2) "learning traps," where the community gets stuck observing suboptimal sources and learns inefficiently. Our main results identify a simple property of the signal correlation structure that separates these outcomes. In both regimes, we characterize which sources are observed in the long run and how often.
Cite
@article{arxiv.1805.08134,
title = {Overabundant Information and Learning Traps},
author = {Annie Liang and Xiaosheng Mu},
journal= {arXiv preprint arXiv:1805.08134},
year = {2018}
}