[2109.14412] Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification

We consider a variant of online binary classification where a learner sequentially assigns labels ( or ) to items with unknown true class. If, but only if, the learner chooses label they immediately observe the true l…

[2109.14412] Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification James A. Grant j.grant@lancaster.ac.uk; corresponding author Department of Mathematics and Statistics, Lancaster University, UK David S. Leslie d.leslie@lancaster.ac.uk Department of Mathematics and Statistics, Lancaster University, UK Abstract We consider a variant of online binary classification where a learner sequentially assigns labels ( 0 0 or 1 1 1 ) to items with unknown true class.

related reading

• 1011.0686arxiv.org
• [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
• [2407.19777] Revisiting Agnostic PAC Learningarxiv.org
• [2506.22401] Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLarxiv.org
• [2510.13651] What is the objective of reasoning with reinforcement learning?arxiv.org
• catoni_draft2.pdfocatoni.perso.math.cnrs.fr
• c21f4ce780c5c9d774f79841b81fdc6d-Paper.pdfproceedings.neurips.cc
• [2602.11399] Can We Really Learn One Representation to Optimize All Rewards?arxiv.org
• A Free Lunch from the Noise:Provable and Practical Exploration for Representation Learningarxiv.org
• Bayes-Optimal Strategiesemergentmind.com
• [2011.01859] A Study of Policy Gradient on a Class of Exactly Solvable Modelsarxiv.org
• [1705.09236] Asynchronous Parallel Bayesian Optimisation via Thompson Samplingarxiv.org