Skip to yearly menu bar Skip to main content


Poster

On Feynman–Kac training of partial Bayesian neural networks

Zheng Zhao · Sebastian Mair · Thomas Schön · Jens Sjölund

MR1 & MR2 - Number 151
[ ] [ Project Page ]
Sat 4 May 6 a.m. PDT — 8:30 a.m. PDT

Abstract:

Recently, partial Bayesian neural networks (pBNNs), which only consider a subset of the parameters to be stochastic, were shown to perform competitively with full Bayesian neural networks. However, pBNNs are often multi-modal in the latent variable space and thus challenging to approximate with parametric models. To address this problem, we propose an efficient sampling-based training strategy, wherein the training of a pBNN is formulated as simulating a Feynman–Kac model. We then describe variations of sequential Monte Carlo samplers that allow us to simultaneously estimate the parameters and the latent posterior distribution of this model at a tractable computational cost. Using various synthetic and real-world datasets we show that our proposed training scheme outperforms the state of the art in terms of predictive performance.

Live content is unavailable. Log in and register to view live content