论文标题
了解消息传递算法的动态：免费的概率启发式方法
Understanding the dynamics of message passing algorithms: a free probability heuristics
论文作者
论文摘要
我们使用随机矩阵理论的Freeness假设来分析具有大型系统极限的概率模型的推理算法的动力学行为。对于玩具模型，我们能够恢复以前的结果，例如消失的有效记忆和算法的分析收敛速率。
We use freeness assumptions of random matrix theory to analyze the dynamical behavior of inference algorithms for probabilistic models with dense coupling matrices in the limit of large systems. For a toy Ising model, we are able to recover previous results such as the property of vanishing effective memories and the analytical convergence rate of the algorithm.
