Deviation-Based Learning

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 choice when she predicts that multiple alternatives will produce a similar payoff.

• Publication year

  2021

• Venue

  arXiv.org

• Publication date

  2021-09-20

• Fields of study

  Mathematics, Computer Science, Economics

• Identifiers
  arXiv 2109.09816
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Bayesian Persuasion

  2024cited by this paper
• Decision Making with Recommendation

  2021cited by this paper
• Contextual Inverse Optimization: Offline and Online Learning

  2021cited by this paper
• Bias and Debias in Recommender System: A Survey and Future Directions

  2020cited by this paper
• Ellipsoidal Methods for Adaptive Choice-Based Conjoint Analysis

  2019cited by this paper
• Recommender Systems as Mechanisms for Social Learning

  2018cited by this paper
• Deconvolving Feedback Loops in Recommender Systems

  2017cited by this paper
• Information Design , Bayesian Persuasion , and Bayes Correlated Equilibrium Information Design , Bayesian Persuasion , and Bayes Correlated Equilibrium

  2016cited by this paper
• Fake It Till You Make It: Reputation, Competition, and Yelp Review Fraud

  2016influential reference
• Social Influence Bias : A Randomized Experiment

  2014cited by this paper
• Bayes Correlated Equilibrium and the Comparison of Information Structures in Games*

  2014cited by this paper
• Promotional Reviews: An Empirical Investigation of Online Review Manipulation

  2014cited by this paper
• Social Influence Bias: A Randomized Experiment

  2013cited by this paper
• Implementing the “Wisdom of the Crowd”

  2013cited by this paper
• Collaborative prediction and ranking with non-random missing data

  2009influential reference
• Approximating the centroid is hard

  2007cited by this paper
• Probabilistic Polyhedral Methods for Adaptive Choice-Based Conjoint Analysis: Theory and Application

  2007cited by this paper
• Experimental Study of Inequality and Unpredictability in an Artificial Cultural Market

  2006cited by this paper
• Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions

  2005cited by this paper
• Solving convex programs by random walks

  2004cited by this paper
• Inverse Optimization

  2001cited by this paper
• Algorithms for Inverse Reinforcement Learning

  2000cited by this paper
• Reinforcement Learning: An Introduction

  1998cited by this paper
• Asymptotically efficient adaptive allocation rules

  1985cited by this paper
• Optimal coordination mechanisms in generalized principal–agent problems

  1982cited by this paper
• An Introduction to Probability Theory and Its Applications

  1959cited by this paper
• Equivalent Comparisons of Experiments

  1953cited by this paper
• A Note on the Pure Theory of Consumer's Behaviour

  1938cited by this paper
• ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLES

  1933cited by this paper
• Asymptotically Efficient Adaptive Allocation Rules

  year unknowncited by this paper

• No citing papers are available for this paper.