The paper introduces a ground‑truth framework for disentangling uncertainty into epistemic and aleatoric components using sample‑conditional pointwise posterior risk. It evaluates current methods, finding that Spectral‑normalized Neural Gaussian Processes and Variational Latent Gaussian Processes best recover the ground‑truth uncertainty, while most methods align more closely with posterior variance and miss predictor bias. The study also explores the entanglement of estimated uncertainties and the impact of modeling choices, providing practical guidance and releasing 13 semi‑synthetic datasets for further validation.
By Frieder Wizgall, Georg Tirpitz, Moritz Seiler, Kerstin Ritter, B\'alint Mucs\'anyi
arXiv:2606. 19353v1 Announce Type: cross Abstract: In-Context Learning (ICL) allows LLMs to adapt to new tasks from a few demonstrations, but its reliability remains a concern: predictions are highly sensitive to both prompt design and the model's ability to understand the context, obscuring whether failures arise from data properties or model limitations.
By Jinseok Chung, Minkyoung Song, Hyunji Jung, Namhoon Lee
arXiv:2607. 14817v1 Announce Type: cross Abstract: Current evaluation of epistemic uncertainty relies on tasks such as out-ofdistribution detection and active learning.
By Jakub Paplh\'am, Willem Waegeman, Eyke H\"ullermeier, Vojt\v{e}ch Franc
arXiv:2602. 08142v2 Announce Type: replace Abstract: Machine learning applications require fast and reliable per-sample uncertainty estimation.
By H. Martin Gillis, Isaac Xu, Thomas Trappenberg
arXiv:2602. 13362v2 Announce Type: replace-cross Abstract: A key challenge in probabilistic regression is ensuring that predictive distributions accurately reflect true empirical uncertainty.
By \'Ad\'am Jung, Domokos M. Kelen, Andr\'as A. Bencz\'ur
arXiv:2607. 28248v1 Announce Type: cross Abstract: The deployment of deep neural networks in safety-critical domains demands reliable estimates of predictive confidence, yet conventional architectures lack principled uncertainty quantification.
By H. Martin Gillis, Thomas Trappenberg
arXiv:2605. 07565v2 Announce Type: replace-cross Abstract: We study Bayesian Optimisation (BO) in settings where the objective function is influenced by uncontrollable environmental contexts governed by an unknown probability distribution.
By Tigran Ramazyan, Denis Derkach
arXiv:2608.29349v1 Announce Type: new
Abstract: Gaussian process (GP) regression with a single global GP (GP-glo) incurs cubic computational cost, limiting scalability to large datasets. Product-of-e...
By Yean Hoon Ong, Paolo Barucca, Wei Pan, Jun Wang
arXiv:2606. 19569v1 Announce Type: new Abstract: Uncertainty quantification (UQ) is essential for reliable decision-making in safety-critical applications in probabilistic machine learning.
By Sam Goring, Tom Kuipers, Nicola Paoletti, David S. Watson
arXiv:2606. 15479v1 Announce Type: cross Abstract: Steerable convolutional neural networks (Steerable-CNNs) guarantee SE(3)-equivariance by parameterizing kernels as linear combinations of steerable basis functions, but their deterministic nature precludes uncertainty quantification - limiting their use in settings where confidence estimates are essential.
By Abhishek Keripale, Ponkrshnan Thiagarajan, Susanta Ghosh
arXiv:2606. 10777v1 Announce Type: new Abstract: Uncertainty estimation is critical for deploying machine learning models in high-stakes settings.
By Arthur Hoarau
arXiv:2605. 00600v2 Announce Type: replace-cross Abstract: Deep neural networks achieve impressive results across diverse applications, yet their overconfidence on unseen inputs necessitates reliable epistemic uncertainty modeling.
By Yao Ni, Jeremie Houssineau, Yew Soon Ong, Piotr Koniusz