Towards Bayesian Data Selection

TL;DR

This paper introduces a Bayesian decision-theoretic framework for data selection in machine learning, deriving optimal criteria and demonstrating their effectiveness in reducing bias across various models.

Contribution

It formulates data selection as a decision problem, derives Bayes-optimal criteria for semi-supervised learning, and empirically shows bias mitigation across multiple models.

Findings

Bayes-optimal data selection criteria reduce confirmation bias.

The method improves model performance on simulated and real data.

Framework applicable to various machine learning models.

Abstract

A wide range of machine learning algorithms iteratively add data to the training sample. Examples include semi-supervised learning, active learning, multi-armed bandits, and Bayesian optimization. We embed this kind of data addition into decision theory by framing data selection as a decision problem. This paves the way for finding Bayes-optimal selections of data. For the illustrative case of self-training in semi-supervised learning, we derive the respective Bayes criterion. We further show that deploying this criterion mitigates the issue of confirmation bias by empirically assessing our method for generalized linear models, semi-parametric generalized additive models, and Bayesian neural networks on simulated and real-world data.