arXiv Machine Learning July 21, 2026 By Sandra Fortini, Kenyon Ng, Sonia Petrone, Judith Rousseau, Susan Wei

Uncertainty Decomposition for Bayes-Filtered Transformers via Bayesian Predictive Inference

Read the original on arXiv Machine Learning →

arXiv:2602. 04596v2 Announce Type: replace-cross Abstract: Bayes-filtered transformers are transformers meta-learned on sequences from a prior predictive distribution to approximate the corresponding posterior predictive distribution.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 7

A Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies

arXiv:2608. 05995v1 Announce Type: new Abstract: Reliable uncertainty estimates are critical in safety-sensitive applications, where understanding the sources of predictive uncertainty is essential.

By Frieder Wizgall, Georg Tirpitz, Moritz Seiler, Kerstin Ritter, B\'alint Mucs\'anyi

benchmarks safety

arXiv Machine Learning

1d ago

A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Risk

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

benchmarks safety

arXiv Machine Learning

Jun 19

Multi-Task Bayesian In-Context Learning

arXiv:2606. 20538v1 Announce Type: new Abstract: Bayesian predictive inference provides a principled framework for uncertainty quantification, data efficiency, and robust generalization.

By Qingyang Zhu, Eric Karl Oermann, Kyunghyun Cho

llms benchmarks

arXiv Machine Learning

Jun 16

In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning

arXiv:2510. 10981v3 Announce Type: replace-cross Abstract: This paper develops a finite-sample statistical theory for in-context learning (ICL), analyzed within a meta-learning framework that accommodates mixtures of diverse task types.

By Tomoya Wakayama, Taiji Suzuki

llms

arXiv Machine Learning

Jun 24

Predictive variational inference: Learn the predictively optimal posterior distribution

arXiv:2410. 14843v4 Announce Type: replace-cross Abstract: Vanilla variational inference finds an optimal approximation to the Bayesian posterior distribution, but even the exact Bayesian posterior is often not meaningful under model misspecification.

By Jinlin Lai, Antonio Linero, Yuling Yao

arXiv Machine Learning

Jun 2

Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features

arXiv:2602. 19126v2 Announce Type: replace Abstract: We propose a robust Bayesian formulation of random feature (RF) regression that accounts explicitly for prior and likelihood misspecification via Huber-style contamination sets.

By Michele Caprio, Katerina Papagiannouli, Siu Lun Chau, Sayan Mukherjee

One email a morning, machine-written

Related stories

A Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies

A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Risk

Multi-Task Bayesian In-Context Learning

In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning

Predictive variational inference: Learn the predictively optimal posterior distribution

Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features