arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.03306cs.ITcs.LGmath.ITmath.STstat.TH
收藏

结构噪声污染下非对称秩一矩阵的失配估计

Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise

Tsinghua University(清华大学);Institute of Science and Technology, Austria(奥地利科学技术研究所);Huawei Technologies Co., Ltd.(华为技术有限公司)

Teng Fu, YuHao Liu, Jean Barbier, Marco Mondelli, ShanSuo Liang, TianQi Hou

摘要:

我们研究了贝叶斯统计学家的性能,他估计了一个被非对称旋转不变噪声破坏的秩一信号,该噪声具有奇异值的通用分布。由于信噪比和噪声结构是未知的,因此错误地假设了高斯设置。我们推导出不匹配贝叶斯估计误差的精确解析表达式,并提供了近似消息传递(AMP)算法的分析。第一个结果利用了矩形矩阵和低秩矩阵扰动的球积分的渐近行为;第二个结果依赖于辅助AMP的设计和分析。数值实验表明,AMP和贝叶斯估计器之间存在性能差距,这是由于不正确的估计信号范数。

英文摘要:

We study the performance of a Bayesian statistician who estimates a rank-one signal corrupted by non-symmetric rotationally invariant noise with a generic distribution of singular values. As the signal-to-noise ratio and the noise structure are unknown, a Gaussian setup is incorrectly assumed. We derive the exact analytic expression for the error of the mismatched Bayes estimator and also provide the analysis of an approximate message passing (AMP) algorithm. The first result exploits the asymptotic behavior of spherical integrals for rectangular matrices and of low-rank matrix perturbations; the second one relies on the design and analysis of an auxiliary AMP. The numerical experiments show that there is a performance gap between the AMP and Bayes estimators, which is due to the incorrect estimation of the signal norm.

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。

↑