all AI news
Deviation-Based Learning: Training Recommender Systems Using Informed User Choice. (arXiv:2109.09816v2 [econ.TH] UPDATED)
stat.ML updates on arXiv.org arxiv.org
This paper proposes a new approach to training recommender systems called
deviation-based learning. The recommender and rational users have different
knowledge. The recommender learns user knowledge by observing what action users
take upon receiving recommendations. Learning eventually stalls if the
recommender always suggests a choice: Before the recommender completes
learning, users start following the recommendations blindly, and their choices
do not reflect their knowledge. The learning rate and social welfare improve
substantially if the recommender abstains from recommending a particular …
arxiv deviation learning recommender systems systems training