Hugging Face Trending Papers August 11, 2026

Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry

Read the original on Hugging Face Trending Papers →

Training neural networks to jointly predict mean and uncertainty estimates from noisy observations can be unstable, prompting a series of independent stabilization efforts. We argue that these interventions highlight a common underlying issue where gradient steps are poorly aligned with the geometry of the loss landscape.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

llms

arXiv Machine Learning

Aug 12

Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry

arXiv:2608. 10374v1 Announce Type: new Abstract: Training neural networks to jointly predict mean and uncertainty estimates from noisy observations can be unstable, prompting a series of independent stabilization efforts.

By Sumedh Vemuganti, Nickvash Kani

llms

arXiv AI

Jun 17

Geometry-Aware Post-Hoc Uncertainty Quantification in Operator Learning

arXiv:2606. 17513v1 Announce Type: cross Abstract: Neural operators provide fast surrogates for PDEs but their deterministic predictions limit their use in tasks requiring uncertainty quantification (UQ), especially under geometric variability.

By Oriol Vendrell-Gallart, Nima Negarandeh, Ramin Bostanabad

rag benchmarks

arXiv Machine Learning

Aug 11

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

arXiv:2608. 07630v1 Announce Type: new 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.

By Pierre Nodet, Thomas George

arXiv Machine Learning

Jul 21

Geometry Adaptive Counterfactual Distribution Learning with Diffusion-Guided Smoothing

arXiv:2605. 25811v2 Announce Type: replace-cross Abstract: We study counterfactual distribution learning for high-dimensional outcomes whose laws may concentrate near lower-dimensional structure.

By Kwangho Kim

rag diffusion

arXiv AI

Jun 30

Representation Learning for Equivariant Inference with Guarantees

arXiv:2505. 19809v3 Announce Type: replace-cross Abstract: In many real-world applications of regression, conditional probability estimation, and uncertainty quantification, exploiting symmetries rooted in physics or geometry can dramatically improve generalization and sample efficiency.

By Daniel Ordo\~nez-Apraez, Vladimir Kosti\'c, Alek Fr\"ohlich, Vivien Brandt, Karim Lounici, Massimiliano Pontil

robotics

arXiv Machine Learning

Aug 6

Robustness Emerges Early in Training Dynamics, but Is Not Preserved

arXiv:2608. 04442v1 Announce Type: new Abstract: Robustness to natural corruptions remains a fundamental challenge for deep neural networks.

By Jiangang Yang, Wenhui Shi, Lu Hu, Jing Xing, Jian Liu

computer-vision benchmarks

Related stories

Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry

Geometry-Aware Post-Hoc Uncertainty Quantification in Operator Learning

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

Geometry Adaptive Counterfactual Distribution Learning with Diffusion-Guided Smoothing

Representation Learning for Equivariant Inference with Guarantees

Robustness Emerges Early in Training Dynamics, but Is Not Preserved