arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1904.03136math.STcs.ITcs.LGmath.ITstat.MLstat.TH
收藏

Monge矩阵的估计

Estimation of Monge Matrices

Massachusetts Institute of Technology(麻省理工学院);Yale University(耶鲁大学)

Jan-Christian Hütter, Cheng Mao, Philippe Rigollet, Elina Robeva

摘要:

蒙奇矩阵和它们的置换形式称为前蒙奇矩阵,自然地出现在科学和工程的许多领域。虽然这些矩阵的丰富结构特性长期以来一直被用于算法目的,但对它们对统计估计的影响知之甚少。在这项工作中,我们建议将这种结构视为一个形状约束和研究的问题,估计蒙氏矩阵加性随机噪声。更具体地说,我们建立了极大极小估计率的Monge和pre-Monge矩阵。在前蒙格矩阵的情况下,最小最大最优最小二乘估计是不能有效地计算,我们提出了两个有效的估计,并建立其收敛速度。我们的理论研究结果得到了数值实验的支持。

英文摘要:

Monge matrices and their permuted versions known as pre-Monge matrices naturally appear in many domains across science and engineering. While the rich structural properties of such matrices have long been leveraged for algorithmic purposes, little is known about their impact on statistical estimation. In this work, we propose to view this structure as a shape constraint and study the problem of estimating a Monge matrix subject to additive random noise. More specifically, we establish the minimax rates of estimation of Monge and pre-Monge matrices. In the case of pre-Monge matrices, the minimax-optimal least-squares estimator is not efficiently computable, and we propose two efficient estimators and establish their rates of convergence. Our theoretical findings are supported by numerical experiments.

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。

↑