Skip to content

Subjective Risk Decomposition: A New View for Uncertainty Quantification

Jul 2026 · arXiv.org · Vol abs/2607.15196 · 1 citation · ⚡ 1 influential · 51 references
Mathematics Computer Science

TL;DR

It is shown how epistemic and aleatoric uncertainty measures can be derived via decomposition of a subjective risk, based on a strictly proper loss, and considered a first step towards a full learning-theoretic framework for uncertainty quantification.

Abstract

We present a novel viewpoint for uncertainty quantification. Uncertainty measures are not primitives, in need of axioms and argumentation, but instead consequences, of higher-level modelling decisions. We show how epistemic and aleatoric uncertainty measures can be derived via decomposition of a subjective risk, based on a strictly proper loss. Reverse cross entropy provides a prominent example, where decomposition recovers the classic information-theoretic uncertainty terms. The same approach recovers numerous measures previously proposed across the UQ literature, providing them a common theoretical foundation. This suggests a new approach to UQ: given a modelling scenario and strictly proper loss, the corresponding epistemic and aleatoric terms are induced by the subjective-risk decomposition. We then extend our view to learning theory: we introduce and analyse subjective risk analogues of excess risk, approximation error and estimation error, and identify the connections to UQ. We consider this a first step towards a full learning-theoretic framework for uncertainty quantification.

View source

Similar papers

Sep 2026

Structural Limits of the Information-Theoretic Uncertainty Decomposition

It is discovered that significant portions of the assumed AU, EU range are infeasible in finite settings, and cannot be attained with any class probabilities, and the infeasible region's boundary helps explain epistemic collapse.

Jakob L. Christensen, Christian F. Baumgartner, M. Hannemose et al. · 0 citations
Preprint Aug 2026

A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Risk

Reliable uncertainty estimates are critical in safety-sensitive applications. For such estimates to be useful in practice, it is crucial to understand the sources underlying a model's uncertainty, motivating the disentanglement of total uncertainty into epistemic and aleatoric uncertainty. Existing notions of uncertain...

Frieder Wizgall, Georg Tirpitz, Moritz Seiler et al. · 2 citations
Preprint Aug 2026

Bayesian Expected Uncertainty Reduction (B-EUR) Model: A Computational Account of What Makes Design Options Worth Trying

The B-EUR model provides a computational account of candidate-action evaluation within uncertainty-driven design activity and offers implications for constructing prototype sets, framing design problems, and organizing feedback to support informative exploration.

Shimon Honda, Takuma Miyaguchi, Koji Koizumi et al. · 0 citations
Preprint Aug 2026

Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making

RATTL targets runtime safety for agents, including LLM-based systems, acting under uncertainty, and proves a Safety Sandwich: the RATTL value lies between the uninformed robust value and the full- knowledge optimum, with a gap that vanishes as the posterior concentrates.

D. Ganguly, Jan Křetinský · 0 citations
Open access Aug 2026

A Bayesian composite risk approach for stochastic optimal control and Markov decision processes

The new modeling paradigm subsumes several classical SOC/MDP formulations, including risk-averse and distributionally robust SOC/MDPs as well as partially observed and Bayes-adaptive MDPs, and generates so-called preference robust SOC/MDP models.

Wen-Tao Ma, Zhi-Ping Chen, Huifu Xu · 1 citation
#artificial intelligence Preprint Aug 2026

Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk

An agent still learning its environment should be cautious while ignorant and bold once confident. The entropic value-at-risk captures this through a robust-optimization identity---a confidence level fixes the radius of a relative-entropy ball of alternative models---but that ball cannot reach catastrophes the nominal...

D. Ganguly, Jan Křetinský · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.