Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification
Grant, James A., Leslie, David S.
–arXiv.org Artificial Intelligence
We consider a variant of online binary classification where a learner sequentially assigns labels ($0$ or $1$) to items with unknown true class. If, but only if, the learner chooses label $1$ they immediately observe the true label of the item. The learner faces a trade-off between short-term classification accuracy and long-term information gain. This problem has previously been studied under the name of the `apple tasting' problem. We revisit this problem as a partial monitoring problem with side information, and focus on the case where item features are linked to true classes via a logistic regression model. Our principal contribution is a study of the performance of Thompson Sampling (TS) for this problem. Using recently developed information-theoretic tools, we show that TS achieves a Bayesian regret bound of an improved order to previous approaches. Further, we experimentally verify that efficient approximations to TS and Information Directed Sampling via P\'{o}lya-Gamma augmentation have superior empirical performance to existing methods.
arXiv.org Artificial Intelligence
Apr-22-2024
- Country:
- Europe
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Switzerland > Zürich
- Zürich (0.04)
- United Kingdom > England
- Asia > Middle East
- Jordan (0.04)
- Europe
- Genre:
- Research Report > New Finding (0.66)
- Industry:
- Education > Educational Setting > Online (1.00)