arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.11335cs.ITmath.IT
收藏

正交/向量AMP的收敛性:长记忆消息传递策略

On the Convergence of Orthogonal/Vector AMP: Long-Memory Message-Passing Strategy

Keigo Takeuchi

摘要:

本文证明了贝叶斯最优正交/向量近似消息传递(AMP)在大系统极限下收敛于不动点。证明是基于贝叶斯最优长记忆(LM)消息传递(MP),保证系统收敛。贝叶斯最优LM-MP的动力学分析通过现有的状态演化框架。证明了所得到的状态演化递推式是收敛的。贝叶斯最优正交/矢量AMP的收敛性证明了确认的状态演化递归的贝叶斯最优正交/矢量AMP的精确减少。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑