论文标题
分析随机顺序消息传递算法以进行近似推断
Analysis of Random Sequential Message Passing Algorithms for Approximate Inference
论文作者
论文摘要
我们在学生教师的场景中分析了传递算法的随机顺序消息传递算法的动力学，以使用大型高斯潜在变量模型进行近似推断。为了建模潜在变量之间的非平凡依赖关系，我们假设从旋转不变合奏中绘制的随机协方差矩阵。此外，我们考虑了模型不匹配的设置，在该设置中，教师模型和学生使用的模型可能不同。通过动态功能方法，我们获得了表征推理算法动力学的精确动力学平均方程。我们还得出了一系列模型参数，顺序算法不会收敛。该参数范围的边界与静态概率模型的复制品对称ANSATZ的de almeida thouless（AT）稳定性条件一致。
We analyze the dynamics of a random sequential message passing algorithm for approximate inference with large Gaussian latent variable models in a student-teacher scenario. To model nontrivial dependencies between the latent variables, we assume random covariance matrices drawn from rotation invariant ensembles. Moreover, we consider a model mismatching setting, where the teacher model and the one used by the student may be different. By means of dynamical functional approach, we obtain exact dynamical mean-field equations characterizing the dynamics of the inference algorithm. We also derive a range of model parameters for which the sequential algorithm does not converge. The boundary of this parameter range coincides with the de Almeida Thouless (AT) stability condition of the replica symmetric ansatz for the static probabilistic model.
