Utilising Gradient-Based Proposals within Sequential Monte Carlo Samplers for Training of Partial Bayesian Neural Networks
Abstract
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. 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 (SOTA) in terms of optimal loss.
Fields of Study & Subjects
Adversarial Robustness in Machine Learning
Gaussian Processes and Bayesian Inference
Generative Adversarial Networks and Image Synthesis
Publication details
- Journal / source
- ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Pages
- 4681–4685
- Publication date
- 21 April 2026
- Language
- EN