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.

翻译：近期研究表明，仅将部分参数视为随机变量的部分贝叶斯神经网络（pBNNs）在全贝叶斯神经网络中展现出竞争性能。然而，pBNNs的隐变量空间常呈现多模态特性，导致参数化模型难以逼近。针对该问题，我们提出了一种基于采样的高效训练策略，将pBNN的训练过程建模为费曼-卡茨模型的模拟。我们随后描述了序列蒙特卡洛采样器的变体，使该模型能以可承受的计算成本同时估计参数与隐后验分布。通过多种合成数据集和真实世界数据集的验证，我们提出的训练方案在预测性能上优于当前最先进方法。