The Delusional Hedge Algorithm as a Model of Human Learning from Diverse Opinions
Abstract: Whereas cognitive models of learning often assume direct experience with both the features of an event and with a true label or outcome, much of everyday learning arises from hearing the opinions of others, without direct access to either the experience or the ground truth outcome. We consider how people can learn which opinions to trust in such scenarios by extending the hedge algorithm: a classic solution for learning from diverse information sources. We first introduce a semi-supervised variant we call the delusional hedge capable of learning from both supervised and unsupervised experiences. In two experiments, we examine the alignment between human judgments and predictions from the standard hedge, the delusional hedge, and a heuristic baseline model. Results indicate that humans effectively incorporate both labeled and unlabeled information in a manner consistent with the delusional hedge algorithm -- suggesting that human learners not only gauge the accuracy of information sources but also their consistency with other reliable sources. The findings advance our understanding of human learning from diverse opinions, with implications for the development of algorithms that better capture how people learn to weigh conflicting information sources.
- (2002). Adaptive and self-confident on-line learning algorithms. Journal of Computer and System Sciences, 64(1), 48–75.
- (2002). Tracking a small set of experts by mixing past posteriors. Journal of Machine Learning Research, 3(Nov), 363–396.
- (2022). When unsupervised training benefits category learning. Cognition, 221, 104984.
- (2006). Prediction, learning, and games. Cambridge university press.
- (2007). Improved second-order bounds for prediction with expert advice. Machine Learning, 66, 321–352.
- (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55(1), 119–139.
- (1999). Adaptive game playing using multiplicative weights. Games and Economic Behavior, 29(1-2), 79–103.
- (2013). Human semi-supervised learning. Topics in cognitive science, 5(1), 132–172.
- (2011). Can semi-supervised learning explain incorrect beliefs about categories? Cognition, 120(1), 106–118.
- (2019). A little labeling goes a long way: Semi-supervised learning in infancy. Developmental science, 22(1), e12736.
- (1994). The weighted majority algorithm. Information and computation, 108(2), 212–261.
- (2019). On the optimality of the hedge algorithm in the stochastic regime. Journal of Machine Learning Research, 20, 1–28.
- (2007). Humans perform semi-supervised classification too. In Proceedings of the 22nd national conference on artificial intelligence - volume 1 (p. 864–869). AAAI Press.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
