Uncertainty quantification for trustworthy deep learning: Methods and measures

• URL: http://arxiv.org/abs/2607.28248v1
• Date: Thu, 30 Jul 2026 14:10:31 GMT
• Title: Uncertainty quantification for trustworthy deep learning: Methods and measures
• Abstract summary: This survey provides a structured, critical review of methods for Uncertainty Quantification in deep learning.<n>Relative to existing UQ surveys, our contribution is depth on efficient ensemble approximations and single-pass methods.<n>We organize methods into five families: Bayesian neural networks, Monte Carlo Dropout, deep ensembles, efficient ensemble approximations, and last-layer or single-pass approaches.
• Score: 0.6857407675150223
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The deployment of deep neural networks in safety-critical domains demands reliable estimates of predictive confidence, yet conventional architectures lack principled uncertainty quantification. This survey provides a structured, critical review of methods for Uncertainty Quantification (UQ) in deep learning, scoped to ensemble-based and approximate Bayesian approaches and the measures used to summarize their outputs. Relative to existing UQ surveys, our contribution is depth on efficient ensemble approximations and single-pass methods, and a unified treatment that separates the method producing a predictive distribution from the measure that summarizes its uncertainty. We organize methods into five families: Bayesian neural networks, Monte Carlo Dropout, deep ensembles, efficient ensemble approximations, and last-layer or single-pass approaches. We situate adjacent work on evidential and prior networks, conformal prediction, and post-hoc calibration, together with the decision-time tasks of out-of-distribution detection and selective prediction. For each, we examine theoretical motivation, implementation, empirical performance, and limitations. We then review ensemble diversity theory and uncertainty measures and their decompositions, contrasting the entropy decomposition with pairwise divergence measures, and consolidate evaluation methodology so that our qualitative comparisons share a common basis. We close with a brief treatment of uncertainty in large language models and open research directions, including efficient epistemic measures for classification, last-layer diversity, diversity and calibration under shift, and hybrid architectures.

Related papers

• Possibilistic Predictive Uncertainty for Deep Learning [75.00607359322863]
  We introduce Dirichlet-approximated possibilistic posterior predictions (DAPPr)<n>DAPPr is a principled framework leveraging possibility theory.<n>This projection-and-approximation strategy yields a simple training objective with closed-form solutions.
  arXiv  Detail & Related papers  (2026-05-01T12:14:01Z)
• Bridging the Gap Between Bayesian Deep Learning and Ensemble Weather Forecasts [100.26854618129039]
  Weather forecasting is fundamentally challenged by the chaotic nature of the atmosphere.<n>Recent advances in Bayesian Deep Learning (BDL) offer a promising but often disconnected alternative.<n>We bridge these paradigms through a unified hybrid BDL framework for ensemble weather forecasting.
  arXiv  Detail & Related papers  (2025-11-18T07:49:52Z)
• Conformal Prediction for Multi-Source Detection on a Network [59.17729745907474]
  We study the multi-source detection problem.<n>Given snapshot observations of node infection status on a graph, estimate the set of source nodes that initiated the propagation.<n>We propose a novel conformal prediction framework that provides statistically valid recall guarantees for source set detection.
  arXiv  Detail & Related papers  (2025-11-12T01:09:56Z)
• Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model [5.624791703748109]
  Uncertainty quantification is a critical aspect of reinforcement learning and deep learning.<n>We propose contextual similarity distillation, a novel approach that explicitly estimates the variance of an ensemble of deep neural networks with a single model.<n>We empirically validate our method across a variety of out-of-distribution detection benchmarks and sparse-reward reinforcement learning environments.
  arXiv  Detail & Related papers  (2025-03-14T12:09:58Z)
• In-Context Parametric Inference: Point or Distribution Estimators? [66.22308335324239]
  We show that amortized point estimators generally outperform posterior inference, though the latter remain competitive in some low-dimensional problems.<n>Our experiments indicate that amortized point estimators generally outperform posterior inference, though the latter remain competitive in some low-dimensional problems.
  arXiv  Detail & Related papers  (2025-02-17T10:00:24Z)
• Exogenous Matching: Learning Good Proposals for Tractable Counterfactual Estimation [1.9662978733004601]
  We propose an importance sampling method for tractable and efficient estimation of counterfactual expressions.<n>By minimizing a common upper bound of counterfactual estimators, we transform the variance minimization problem into a conditional distribution learning problem.<n>We validate the theoretical results through experiments under various types and settings of Structural Causal Models (SCMs) and demonstrate the outperformance on counterfactual estimation tasks.
  arXiv  Detail & Related papers  (2024-10-17T03:08:28Z)
• Predictive Inference in Multi-environment Scenarios [18.324321417099394]
  We address the challenge of constructing valid confidence intervals and sets in problems of prediction across multiple environments. We extend the jackknife and split-conformal methods to show how to obtain distribution-free coverage in non-traditional, potentially hierarchical data-generating scenarios. Our contributions also include extensions for settings with non-real-valued responses, a theory of consistency for predictive inference in these general problems, and insights on the limits of conditional coverage.
  arXiv  Detail & Related papers  (2024-03-25T00:21:34Z)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• Fast Uncertainty Estimates in Deep Learning Interatomic Potentials [0.0]
  We propose a method to estimate the predictive uncertainty based on a single neural network without the need for an ensemble. We demonstrate that the quality of the uncertainty estimates matches those obtained from deep ensembles.
  arXiv  Detail & Related papers  (2022-11-17T20:13:39Z)
• Uncertainty Quantification for Traffic Forecasting: A Unified Approach [21.556559649467328]
  Uncertainty is an essential consideration for time series forecasting tasks. In this work, we focus on quantifying the uncertainty of traffic forecasting. We develop Deep S-Temporal Uncertainty Quantification (STUQ), which can estimate both aleatoric and relational uncertainty.
  arXiv  Detail & Related papers  (2022-08-11T15:21:53Z)
• Quantifying Uncertainty in Deep Spatiotemporal Forecasting [67.77102283276409]
  We describe two types of forecasting problems: regular grid-based and graph-based. We analyze UQ methods from both the Bayesian and the frequentist point view, casting in a unified framework via statistical decision theory. Through extensive experiments on real-world road network traffic, epidemics, and air quality forecasting tasks, we reveal the statistical computational trade-offs for different UQ methods.
  arXiv  Detail & Related papers  (2021-05-25T14:35:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.