Stochastic variational inference is an established way to carry out approximate Bayesian inference for deep models. While there have been effective proposals for good initializations for loss minimization in deep learning, far less attention has been devoted to the issue of initialization of stochastic variational inference. We address this by proposing a novel layer-wise initialization strategy based on Bayesian linear models. The proposed method is extensively validated on regression and classification tasks, including Bayesian DeepNets and ConvNets, showing faster convergence compared to alternatives inspired by the literature on initializations for loss minimization.

翻译：在深层研究中,虽然已经提出了妥善初始化以尽量减少损失的有效建议,但对初始化的随机变异性推断问题的关注却少得多,我们通过提出一种基于巴耶斯线性模型的新颖的、从层到层的初始化战略来解决这一问题,拟议的方法在回归和分类任务(包括巴耶斯深海网络和ConvNets)上得到广泛验证,与关于最小化损失初始化的文献所启发的替代方法相比,这些方法的趋同速度更快。