Pith. sign in

Approximate blocked Gibbs sampling for Bayesian neural networks

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

In this work, minibatch MCMC sampling for feedforward neural networks is made more feasible. To this end, it is proposed to sample subgroups of parameters via a blocked Gibbs sampling scheme. By partitioning the parameter space, sampling is possible irrespective of layer width. It is also possible to alleviate vanishing acceptance rates for increasing depth by reducing the proposal variance in deeper layers. Increasing the length of a non-convergent chain increases the predictive accuracy in classification tasks, so avoiding vanishing acceptance rates and consequently enabling longer chain runs have practical benefits. Moreover, non-convergent chain realizations aid in the quantification of predictive uncertainty. An open problem is how to perform minibatch MCMC sampling for feedforward neural networks in the presence of augmented data.

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Approximate Message Passing for Bayesian Neural Networks

cs.LG · 2025-01-26 · conditional · novelty 6.0

A factor-graph message-passing method for Bayesian neural networks that handles CNNs, avoids double-counting, and shows competitive accuracy with improved calibration on CIFAR-10.

citing papers explorer

Showing 1 of 1 citing paper.

  • Approximate Message Passing for Bayesian Neural Networks cs.LG · 2025-01-26 · conditional · none · ref 21 · internal anchor

    A factor-graph message-passing method for Bayesian neural networks that handles CNNs, avoids double-counting, and shows competitive accuracy with improved calibration on CIFAR-10.