arXiv Statistics ML October 26, 2026 By August Arnstad, Geir Olve Storvik, Filippo Pagani, Leiv R{\o}nneberg

Sparse Bayesian Neural Networks via Sticky Piecewise Deterministic Markov Processes

Read the original on arXiv Statistics ML →

The paper introduces a method for training sparse Bayesian neural networks by integrating spike-and-slab priors into sticky piecewise deterministic Markov processes (PDMPs). It demonstrates that these modern Monte Carlo techniques can sample posterior distributions of Bayesian neural networks exactly, provided numerical rate bounds are satisfied. Experiments show that the resulting sparse models not only converge well but also exhibit greater robustness to input noise compared to their dense counterparts.

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 Statistics ML.

efficiency

arXiv Machine Learning

Oct 8

Sparsifying Stochasticity, Not Capacity: Partial Stochasticity via Deep Weight Factorization of Prior Scales

arXiv:2610.09886v1 Announce Type: cross Abstract: Bayesian neural networks need not be fully stochastic to be universal conditional density approximators, but it remains open which parameters should...

By Marius P Linhard, Maurizio Filippone

benchmarks

arXiv Machine Learning

Oct 15

Theoretical and Practical Advances in Hierarchical Bayesian Deep Learning Methodology

arXiv:2610.19074v1 Announce Type: new Abstract: Reliable uncertainty quantification remains an important challenge in AI. Hierarchical Bayesian methods provide a principled framework for this by repr...

By Neil K. Chada, Simon Cotter, Kody J. H. Law, Xinzhu Liang

arXiv Machine Learning

Aug 11

Path-dependent Discrete Amortized Inference

arXiv:2608. 08644v1 Announce Type: new Abstract: We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution.

By Tiago da Silva, Esmeralda S. Whitammer, Salem Lahlou

reinforcement-learning benchmarks

arXiv Machine Learning

Jul 17

Neural Architectures for Amortized Bayesian Inference: Statistical Foundations and Empirical Assessments

arXiv:2601. 07944v2 Announce Type: replace-cross Abstract: Since the turn of the century, approximate Bayesian inference has steadily evolved as new computational techniques have been incorporated to handle increasingly complex, large-scale predictive problems.

By Roy Shivam Ram Shreshtth, Arnab Hazra, Gourab Mukherjee

llms efficiency

arXiv AI

Oct 9

When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees

The paper introduces a method that uses confidence sequences to adaptively determine the number of Monte Carlo samples needed for Bayesian neural network predictions, ensuring statistical guarantees. It applies to tasks such as class identification, full predictive distribution approximation, and probability-threshold decisions, stopping sampling once the desired confidence is achieved. Experiments demonstrate efficient computational budgeting, allocating more samples to ambiguous inputs, preserving decision reliability, and reducing overall latency compared to a fixed sample budget.

By Fabian Denoodt, Sibylle Hess

arXiv Machine Learning

Aug 5

Divide-and-Conquer: Towards Generalizable Amortized Bayesian Inference for the Drift Diffusion Model

arXiv:2608. 03566v1 Announce Type: cross Abstract: The drift diffusion model (DDM) is a cornerstone of cognitive decision-making research.

By Yufei Wu, Shanqing Gao, Andreas Voss, Francis Tuerlinckx

diffusion

One email a morning, machine-written

Related stories

Sparsifying Stochasticity, Not Capacity: Partial Stochasticity via Deep Weight Factorization of Prior Scales

Theoretical and Practical Advances in Hierarchical Bayesian Deep Learning Methodology

Path-dependent Discrete Amortized Inference

Neural Architectures for Amortized Bayesian Inference: Statistical Foundations and Empirical Assessments

When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees

Divide-and-Conquer: Towards Generalizable Amortized Bayesian Inference for the Drift Diffusion Model