Variational EP with Probabilistic Backpropagation for Bayesian Neural Networks

arXiv (Cornell University)(2023)

引用 0|浏览1
暂无评分
摘要
I propose a novel approach for nonlinear Logistic regression using a two-layer neural network (NN) model structure with hierarchical priors on the network weights. I present a hybrid of expectation propagation called Variational Expectation Propagation approach (VEP) for approximate integration over the posterior distribution of the weights, the hierarchical scale parameters of the priors and zeta. Using a factorized posterior approximation I derive a computationally efficient algorithm, whose complexity scales similarly to an ensemble of independent sparse logistic models. The approach can be extended beyond standard activation functions and NN model structures to form flexible nonlinear binary predictors from multiple sparse linear models. I consider a hierarchical Bayesian model with logistic regression likelihood and a Gaussian prior distribution over the parameters called weights and hyperparameters. I work in the perspective of E step and M step for computing the approximating posterior and updating the parameters using the computed posterior respectively.
更多
查看译文
关键词
probabilistic backpropagation,bayesian neural
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要