论文标题
部分可观测时空混沌系统的无模型预测
On the Convergence of Orthogonal/Vector AMP: Long-Memory Message-Passing Strategy
论文作者
论文摘要
本文证明了贝叶斯最佳的正交/矢量近似消息通话（AMP）的收敛性与大型系统限制中的固定点的融合。该证明是基于贝叶斯最佳的长官（LM）消息通话（MP），该消息可以系统地收敛。通过现有的状态进化框架分析了贝叶斯最佳LM-MP的动力学。获得的状态进化递归被证明是融合的。贝叶斯最佳正交/矢量放大器的收敛性通过确认对贝叶斯正交/矢量放大器的状态进化递归的确切减少来证明。
This paper proves the convergence of Bayes-optimal orthogonal/vector approximate message-passing (AMP) to a fixed point in the large system limit. The proof is based on Bayes-optimal long-memory (LM) message-passing (MP) that is guaranteed to converge systematically. The dynamics of Bayes-optimal LM-MP is analyzed via an existing state evolution framework. The obtained state evolution recursions are proved to converge. The convergence of Bayes-optimal orthogonal/vector AMP is proved by confirming an exact reduction of the state evolution recursions to those for Bayes-optimal orthogonal/vector AMP.
