[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

• Bayesian Neural Networkscs.toronto.edu
• Learning to be Bayesian without Supervisionpapers.nips.cc
• The Bayes Banditfrancesco215.github.io
• The Multi-Armed Bandit Problem and Its Solutions | Lil'Loglilianweng.github.io
• A Course in Machine Learningciml.info
• Lecture 1: Introduction to Sequence Prediction | CS 8803 Sequence Predictionthejakeyboy.github.io
• Bayesian programming - Wikipediaen.wikipedia.org
• empirical_bayes_without_prior_or_supervision_raphan.pdfcns.nyu.edu
• Gregory Gundersengregorygundersen.com
• Competing with sampling — Alignment Research Centeralignment.org
• Classificationfairmlbook.org
• arxiv.org/pdf/1805.08522arxiv.org