arXiv Machine Learning July 7, 2026 By Pavel Prochazka

Direct Bethe Free Energy Minimization for Bayesian Neural Networks

Read the original on arXiv Machine Learning →

arXiv:2605. 08446v3 Announce Type: replace Abstract: Bayesian neural networks are typically trained against the evidence lower bound (ELBO), whose Jensen gap closes only when the variational posterior is exact.

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

Jul 7

Gradient Descent as Implicit EM in Distance-Based Neural Models

arXiv:2512. 24780v2 Announce Type: replace Abstract: Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking.

By Alan Oursland

llms

arXiv Machine Learning

Jul 7

Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average

arXiv:2607. 03809v1 Announce Type: new Abstract: Normalising flows provide a powerful variational family for approximate inference, yet individual architectures often fail to generalise across heterogeneous posterior geometries.

By Benjamin Wiriyapong, Oktay Karakus, Can Eyupoglu, Kirill Sidorov

multimodal benchmarks

arXiv Computation and Language

3d ago

Learning Functional Subspaces for Neural Network Compression

arXiv:2609.40127v1 Announce Type: cross Abstract: Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keepin...

By Massimo Bini, Anders Christensen, Stephan Alaniz, Judah Goldfeder, Ole Winther, Yann LeCun, Ravid Shwartz-Ziv, Zeynep Akata

llms efficiency

arXiv AI

Jul 7

Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks

arXiv:2503. 10496v2 Announce Type: replace-cross Abstract: Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions.

By Eirik H{\o}yheim, Lars Skaaret-Lund, Solve S{\ae}b{\o}, Aliaksandr Hubin

benchmarks

arXiv Statistics ML

3d ago

Mitigating Representation Gaps in Amortized Bayesian Inference with Auxiliary Supervision

arXiv:2609.39525v1 Announce Type: new Abstract: Casting Bayesian inference as a neural network optimization problem targeting an amortized posterior is attractive, as it extends to otherwise intracta...

By Hans Olischl\"ager, Svenja Jedhoff, \v{S}imon Kucharsk\'y, Aayush Mishra, Stefan T. Radev, Paul B\"urkner

arXiv Machine Learning

Aug 26

Focal Calibration Loss: Controlling Posterior Distortion in Deep Neural Classifiers

arXiv:2410.18321v3 Announce Type: replace Abstract: Confidence calibration matters wherever a classifier's probabilities, not just its labels, are consumed downstream. We study Focal Calibration Loss...

By Wenhao Liang, Liangwei Zheng, Wei Zhang, Weitong Chen

llms safety

One email a morning, machine-written

Related stories

Gradient Descent as Implicit EM in Distance-Based Neural Models

Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average

Learning Functional Subspaces for Neural Network Compression

Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks

Mitigating Representation Gaps in Amortized Bayesian Inference with Auxiliary Supervision

Focal Calibration Loss: Controlling Posterior Distortion in Deep Neural Classifiers