On the Difficulty of Epistemic Uncertainty Quantification in Machine Learning: The Case of Direct Uncertainty Estimation through Loss Minimisation

• URL: http://arxiv.org/abs/2203.06102v1
• Date: Fri, 11 Mar 2022 17:26:05 GMT
• Title: On the Difficulty of Epistemic Uncertainty Quantification in Machine Learning: The Case of Direct Uncertainty Estimation through Loss Minimisation
• Authors: Viktor Bengs, Eyke H\"ullermeier, Willem Waegeman
• Abstract summary: Uncertainty quantification has received increasing attention in machine learning. The latter refers to the learner's (lack of) knowledge and appears to be especially difficult to measure and quantify. We show that loss minimisation does not work for second-order predictors.
• Score: 8.298716599039501
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Uncertainty quantification has received increasing attention in machine learning in the recent past. In particular, a distinction between aleatoric and epistemic uncertainty has been found useful in this regard. The latter refers to the learner's (lack of) knowledge and appears to be especially difficult to measure and quantify. In this paper, we analyse a recent proposal based on the idea of a second-order learner, which yields predictions in the form of distributions over probability distributions. While standard (first-order) learners can be trained to predict accurate probabilities, namely by minimising suitable loss functions on sample data, we show that loss minimisation does not work for second-order predictors: The loss functions proposed for inducing such predictors do not incentivise the learner to represent its epistemic uncertainty in a faithful way.

Related papers

• Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods? [12.88166582566313]
  This paper presents novel theoretical insights of evidential deep learning. It highlights the difficulties in optimizing second-order loss functions. It provides novel insights into issues of identifiability and convergence in second-order loss minimization.
  arXiv  Detail & Related papers  (2024-02-14T10:07:05Z)
• Quantification of Predictive Uncertainty via Inference-Time Sampling [57.749601811982096]
  We propose a post-hoc sampling strategy for estimating predictive uncertainty accounting for data ambiguity. The method can generate different plausible outputs for a given input and does not assume parametric forms of predictive distributions.
  arXiv  Detail & Related papers  (2023-08-03T12:43:21Z)
• Model-Based Uncertainty in Value Functions [89.31922008981735]
  We focus on characterizing the variance over values induced by a distribution over MDPs. Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation. We propose a new uncertainty Bellman equation whose solution converges to the true posterior variance over values.
  arXiv  Detail & Related papers  (2023-02-24T09:18:27Z)
• On Second-Order Scoring Rules for Epistemic Uncertainty Quantification [8.298716599039501]
  We show that there seems to be no loss function that provides an incentive for a second-order learner to faithfully represent its uncertainty. As a main mathematical tool to prove this result, we introduce the generalised notion of second-order scoring rules.
  arXiv  Detail & Related papers  (2023-01-30T08:59:45Z)
• A Cautionary Tale of Decorrelating Theory Uncertainties [0.5076419064097732]
  We will discuss techniques to train machine learning classifiers that are independent of a given feature. We will examine theory uncertainties, which typically do not have a statistical origin. We will provide explicit examples of two-point (fragmentation modeling) and continuous (higher-order corrections) uncertainties where decorrelating significantly reduces the apparent uncertainty.
  arXiv  Detail & Related papers  (2021-09-16T18:00:01Z)
• Exploring Uncertainty in Deep Learning for Construction of Prediction Intervals [27.569681578957645]
  We explore the uncertainty in deep learning to construct prediction intervals. We design a special loss function, which enables us to learn uncertainty without uncertainty label. Our method correlates the construction of prediction intervals with the uncertainty estimation.
  arXiv  Detail & Related papers  (2021-04-27T02:58:20Z)
• 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)
• The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
  The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
  arXiv  Detail & Related papers  (2020-12-05T17:30:35Z)
• Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions [121.10450359856242]
  We develop a frequentist procedure that utilizes influence functions of a model's loss functional to construct a jackknife (or leave-one-out) estimator of predictive confidence intervals. The DJ satisfies (1) and (2), is applicable to a wide range of deep learning models, is easy to implement, and can be applied in a post-hoc fashion without interfering with model training or compromising its accuracy.
  arXiv  Detail & Related papers  (2020-06-29T13:36:52Z)
• Learning to Predict Error for MRI Reconstruction [67.76632988696943]
  We demonstrate that predictive uncertainty estimated by the current methods does not highly correlate with prediction error. We propose a novel method that estimates the target labels and magnitude of the prediction error in two steps.
  arXiv  Detail & Related papers  (2020-02-13T15:55:32Z)

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.