A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learning

TL;DR

This paper provides a comprehensive review of uncertainty in machine learning and deep learning, covering its categories, sources, quantification methods, and implications for decision-making, with a focus on recent advances in deep learning techniques.

Contribution

It offers an updated, structured overview of uncertainty quantification methods in deep learning, broadening the scope of existing literature and integrating various facets of uncertainty analysis.

Findings

Detailed categorization of uncertainty types and sources.

Evaluation of metrics for uncertainty quantification and calibration.

Discussion on decision-making processes under uncertainty.

Abstract

The adaptation and use of Machine Learning (ML) in our daily lives has led to concerns in lack of transparency, privacy, reliability, among others. As a result, we are seeing research in niche areas such as interpretability, causality, bias and fairness, and reliability. In this survey paper, we focus on a critical concern for adaptation of ML in risk-sensitive applications, namely understanding and quantifying uncertainty. Our paper approaches this topic in a structured way, providing a review of the literature in the various facets that uncertainty is enveloped in the ML process. We begin by defining uncertainty and its categories (e.g., aleatoric and epistemic), understanding sources of uncertainty (e.g., data and model), and how uncertainty can be assessed in terms of uncertainty quantification techniques (Ensembles, Bayesian Neural Networks, etc.). As part of our assessment and understanding of uncertainty in the ML realm, we cover metrics for uncertainty quantification for a single sample, dataset, and metrics for accuracy of the uncertainty estimation itself. This is followed by discussions on calibration (model and uncertainty), and decision making under uncertainty. Thus, we provide a more complete treatment of uncertainty: from the sources of uncertainty to the decision-making process. We have focused the review of uncertainty quantification methods on Deep Learning (DL), while providing the necessary background for uncertainty discussion within ML in general. Key contributions in this review are broadening the scope of uncertainty discussion, as well as an updated review of uncertainty quantification methods in DL.