Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators

• URL: http://arxiv.org/abs/2608.07630v1
• Date: Fri, 07 Aug 2026 12:18:52 GMT
• Title: Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators
• Abstract summary: We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning.<n>Our approach leverages recent advances in approximate Fisher Information Matrices to enable scaling to actual architectures.
• Score: 0.13685626568919942
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty attributable to two sources : aleatoric uncertainty, or locally scarce data. Our approach leverages recent advances in approximate Fisher Information Matrices, to enable scaling to actual architectures. Experimental results demonstrate how each test points is differentially impacted by both sources, highlighting the practical utility of our estimators in improving the robustness of real-world applications.

Related papers

• A Knowledge-Informed Pretrained Model for Causal Discovery [61.8885572392623]
  Causal discovery has been widely studied, yet many existing methods rely on strong assumptions or fall into two extremes.<n>We propose a knowledge-informed pretrained model for causal discovery that integrates weak prior knowledge as a principled middle ground.<n>Our model adopts a dual source encoder-decoder architecture to process observational data in a knowledge-informed way.
  arXiv  Detail & Related papers  (2026-03-21T14:59:41Z)
• Towards Uncertainty Quantification in Generative Model Learning [3.498371632913735]
  We formalize the problem of uncertainty quantification in generative model learning.<n>Preliminary experiments on synthetic datasets demonstrate the effectiveness of aggregated precision-recall curves.
  arXiv  Detail & Related papers  (2025-11-13T09:01:12Z)
• Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation [68.106428321492]
  Large language models (LLMs) demonstrate advanced reasoning abilities, enabling robots to understand natural language instructions and generate high-level plans with appropriate grounding.<n>LLMs hallucinations present a significant challenge, often leading to overconfident yet potentially misaligned or unsafe plans.<n>We present Combined Uncertainty estimation for Reliable Embodied planning (CURE), which decomposes the uncertainty into epistemic and intrinsic uncertainty, each estimated separately.
  arXiv  Detail & Related papers  (2025-10-09T10:26:58Z)
• TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbation [11.334867025651233]
  We propose TULiP, a theoretically-driven uncertainty estimator for OOD detection.<n>Our approach considers a hypothetical perturbation applied to the network before convergence.<n>Our method exhibits state-of-the-art performance, particularly for near-distribution samples.
  arXiv  Detail & Related papers  (2025-05-22T17:16:41Z)
• Uncertainty for Active Learning on Graphs [70.44714133412592]
  Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models.<n>We benchmark Uncertainty Sampling beyond predictive uncertainty and highlight a significant performance gap to other Active Learning strategies.<n>We develop ground-truth Bayesian uncertainty estimates in terms of the data generating process and prove their effectiveness in guiding Uncertainty Sampling toward optimal queries.
  arXiv  Detail & Related papers  (2024-05-02T16:50:47Z)
• One step closer to unbiased aleatoric uncertainty estimation [71.55174353766289]
  We propose a new estimation method by actively de-noising the observed data. By conducting a broad range of experiments, we demonstrate that our proposed approach provides a much closer approximation to the actual data uncertainty than the standard method.
  arXiv  Detail & Related papers  (2023-12-16T14:59:11Z)
• Uncertainty Estimation by Fisher Information-based Evidential Deep Learning [61.94125052118442]
  Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL) In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
  arXiv  Detail & Related papers  (2023-03-03T16:12:59Z)
• Quantifying Epistemic Uncertainty in Deep Learning [15.494774321257939]
  Uncertainty quantification is at the core of the reliability and robustness of machine learning. We provide a theoretical framework to dissect the uncertainty, especially the textitepistemic component, in deep learning. We propose two approaches to estimate these uncertainties, one based on influence function and one on variability.
  arXiv  Detail & Related papers  (2021-10-23T03:21:10Z)
• DEUP: Direct Epistemic Uncertainty Prediction [56.087230230128185]
  Epistemic uncertainty is part of out-of-sample prediction error due to the lack of knowledge of the learner. We propose a principled approach for directly estimating epistemic uncertainty by learning to predict generalization error and subtracting an estimate of aleatoric uncertainty.
  arXiv  Detail & Related papers  (2021-02-16T23:50:35Z)
• Weight-of-evidence 2.0 with shrinkage and spline-binning [3.925373521409752]
  We propose a formalized, data-driven and powerful method to transform categorical predictors. We extend upon the weight-of-evidence approach and propose to estimate the proportions using shrinkage estimators. We present the results of a series of experiments in a fraud detection setting, which illustrate the effectiveness of the presented approach.
  arXiv  Detail & Related papers  (2021-01-05T13:13:16Z)
• Uncertainty Quantification in Extreme Learning Machine: Analytical Developments, Variance Estimates and Confidence Intervals [0.0]
  Uncertainty quantification is crucial to assess prediction quality of a machine learning model. Most methods proposed in the literature make strong assumptions on the data, ignore the randomness of input weights or neglect the bias contribution in confidence interval estimations. This paper presents novel estimations that overcome these constraints and improve the understanding of ELM variability.
  arXiv  Detail & Related papers  (2020-11-03T13:45:59Z)

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.