Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping

TL;DR

This paper investigates how prior functions and bootstrapping enhance ensemble methods for uncertainty estimation, demonstrating their benefits through theoretical analysis and experiments, especially in varying noise conditions.

Contribution

It provides a comprehensive analysis of the roles of prior functions and bootstrapping in ensemble uncertainty estimation, clarifying their importance and benefits.

Findings

Prior functions improve joint predictions across inputs.

Bootstrapping offers additional benefits with varying noise levels.

Both ingredients significantly enhance ensemble performance.

Abstract

In machine learning, an agent needs to estimate uncertainty to efficiently explore and adapt and to make effective decisions. A common approach to uncertainty estimation maintains an ensemble of models. In recent years, several approaches have been proposed for training ensembles, and conflicting views prevail with regards to the importance of various ingredients of these approaches. In this paper, we aim to address the benefits of two ingredients -- prior functions and bootstrapping -- which have come into question. We show that prior functions can significantly improve an ensemble agent's joint predictions across inputs and that bootstrapping affords additional benefits if the signal-to-noise ratio varies across inputs. Our claims are justified by both theoretical and experimental results.