论文标题
缩放哈密顿的蒙特卡洛推断贝叶斯神经网络具有对称分裂
Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting
论文作者
论文摘要
汉密尔顿蒙特卡洛（HMC）是马尔可夫链蒙特卡洛（MCMC）方法，在高维模型（例如神经网络）中具有有利的探索性能。不幸的是，HMC在大型DATA政权中的使用有限，很少的工作探索了旨在保留整个汉密尔顿人的合适方法。在我们的工作中，我们引入了一种不依赖随机梯度的新型对称集成方案，该方案不依赖于随机梯度。我们表明，我们的新配方比以前的方法更有效，并且使用单个GPU易于实现。结果，我们能够使用整个数据集对通用深度学习架构进行完整的HMC。此外，当我们与随机梯度MCMC进行比较时，我们表明我们的方法在准确性和不确定性定量方面都可以更好地性能。在考虑针对大规模机器学习问题的推理方案时，我们的方法将HMC作为可行的选择。
Hamiltonian Monte Carlo (HMC) is a Markov chain Monte Carlo (MCMC) approach that exhibits favourable exploration properties in high-dimensional models such as neural networks. Unfortunately, HMC has limited use in large-data regimes and little work has explored suitable approaches that aim to preserve the entire Hamiltonian. In our work, we introduce a new symmetric integration scheme for split HMC that does not rely on stochastic gradients. We show that our new formulation is more efficient than previous approaches and is easy to implement with a single GPU. As a result, we are able to perform full HMC over common deep learning architectures using entire data sets. In addition, when we compare with stochastic gradient MCMC, we show that our method achieves better performance in both accuracy and uncertainty quantification. Our approach demonstrates HMC as a feasible option when considering inference schemes for large-scale machine learning problems.
