Enregistré dans:
Détails bibliographiques
Auteurs principaux: Millard, Andrew, Murphy, Joshua, Maskell, Simon, Zhao, Zheng
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.03797
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
Table des matières:
  • Partial Bayesian neural networks (pBNNs) have been shown to perform competitively with fully Bayesian neural networks while only having a subset of the parameters be stochastic. Using sequential Monte Carlo (SMC) samplers as the inference method for pBNNs gives a non-parametric probabilistic estimation of the stochastic parameters, and has shown improved performance over parametric methods. In this paper we introduce a new SMC-based training method for pBNNs by utilising a guided proposal and incorporating gradient-based Markov kernels, which gives us better scalability on high dimensional problems. We show that our new method outperforms the state-of-the-art in terms of predictive performance and optimal loss. We also show that pBNNs scale well with larger batch sizes, resulting in significantly reduced training times and often better performance.