Adaptive Sampling Policies Imply Biased Beliefs: A Generalization of the Hot Stove Effect
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910397289725952 |
|---|---|
| author | Denrell, Jerker |
| author_facet | Denrell, Jerker |
| contents | The Hot Stove Effect is a negativity bias resulting from the adaptive character of learning. The mechanism is that learning algorithms that pursue alternatives with positive estimated values, but avoid alternatives with negative estimated values, will correct errors of overestimation but fail to correct errors of underestimation. Here, we generalize the theory behind the Hot Stove Effect to settings in which negative estimates do not necessarily lead to avoidance but to a smaller sample size (i.e., a learner selects fewer of alternative B if B is believed to be inferior but does not entirely avoid B). We formally demonstrate that the negativity bias remains in this set-up. We also show there is a negativity bias for Bayesian learners in the sense that most such learners underestimate the expected value of an alternative. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_02591 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Sampling Policies Imply Biased Beliefs: A Generalization of the Hot Stove Effect Denrell, Jerker Machine Learning The Hot Stove Effect is a negativity bias resulting from the adaptive character of learning. The mechanism is that learning algorithms that pursue alternatives with positive estimated values, but avoid alternatives with negative estimated values, will correct errors of overestimation but fail to correct errors of underestimation. Here, we generalize the theory behind the Hot Stove Effect to settings in which negative estimates do not necessarily lead to avoidance but to a smaller sample size (i.e., a learner selects fewer of alternative B if B is believed to be inferior but does not entirely avoid B). We formally demonstrate that the negativity bias remains in this set-up. We also show there is a negativity bias for Bayesian learners in the sense that most such learners underestimate the expected value of an alternative. |
| title | Adaptive Sampling Policies Imply Biased Beliefs: A Generalization of the Hot Stove Effect |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.02591 |