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

09/29/2021
by   James A. Grant, et al.
0

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 Pólya-Gamma augmentation have superior empirical performance to existing methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/08/2015

The Knowledge Gradient with Logistic Belief Models for Binary Classification

We consider sequential decision making problems for binary classificatio...
research
10/28/2021

Selective Sampling for Online Best-arm Identification

This work considers the problem of selective-sampling for best-arm ident...
research
11/14/2019

A Bayesian/Information Theoretic Model of Bias Learning

In this paper the problem of learning appropriate bias for an environmen...
research
05/18/2018

PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits

We address the problem of regret minimization in logistic contextual ban...
research
02/17/2020

Causal Feature Discovery through Strategic Modification

We consider an online regression setting in which individuals adapt to t...
research
08/06/2023

Self-Directed Linear Classification

In online classification, a learner is presented with a sequence of exam...
research
08/27/2023

Online GentleAdaBoost – Technical Report

We study the online variant of GentleAdaboost, where we combine a weak l...

Please sign up or login with your details

Forgot password? Click here to reset