论文标题
贝叶斯神经网络的可行近似高斯推断
Tractable Approximate Gaussian Inference for Bayesian Neural Networks
论文作者
论文摘要
在本文中，我们提出了一种分析方法，用于在贝叶斯神经网络中执行可拖动的近似高斯推断（Tagi）。该方法使后平均值载体和对角线协方差矩阵的分析高斯推断，重量和偏见。提出的方法的计算复杂性相对于参数$ n $的数量为$ \ MATHCAL {O}（n）$，并且对回归和分类基准进行的测试确认，对于相同的网络体系结构，它与依赖梯度反向启动的现有方法的性能相匹配。
In this paper, we propose an analytical method for performing tractable approximate Gaussian inference (TAGI) in Bayesian neural networks. The method enables the analytical Gaussian inference of the posterior mean vector and diagonal covariance matrix for weights and biases. The method proposed has a computational complexity of $\mathcal{O}(n)$ with respect to the number of parameters $n$, and the tests performed on regression and classification benchmarks confirm that, for a same network architecture, it matches the performance of existing methods relying on gradient backpropagation.
