arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.12031stat.MLcs.LGcs.NAmath.NAmath.OCstat.ME
收藏

基于黎曼高斯-牛顿法的低秩张量估计:统计最优性与二阶收敛性

Low-rank Tensor Estimation via Riemannian Gauss-Newton: Statistical Optimality and Second-Order Convergence

University of Chicago(芝加哥大学);Duke University(杜克大学)

Yuetian Luo, Anru R. Zhang

AI总结:

本文针对含噪线性测量下的低 Tucker 秩张量估计问题,提出黎曼高斯-牛顿方法,首次证明其在含噪环境下的局部二次收敛性,并给出匹配的误差上下界以证明统计最优性,通过张量回归和张量 SVD 应用及仿真验证了理论结果。

摘要:

本文研究从若干含噪线性测量中估计低 Tucker 秩张量的问题。该一般性问题涵盖应用中出现的许多具体例子,包括张量回归、张量补全以及张量 PCA/SVD。我们考虑一种用于低 Tucker 秩张量估计的高效黎曼高斯-牛顿(RGN)方法。与文献中 RGN 的一般(超)线性收敛保证不同,我们在一定正则性条件下,首次证明了 RGN 在含噪环境下用于低秩张量估计的局部二次收敛保证,并给出了相应的估计误差上界。我们还提供了一个与上界相匹配的确定性估计误差下界,从而证明了 RGN 的统计最优性。通过两个机器学习应用——张量回归和张量 SVD——展示了 RGN 的优点。最后,我们给出仿真结果以佐证我们的理论发现。

英文摘要:

In this paper, we consider the estimation of a low Tucker rank tensor from a number of noisy linear measurements. The general problem covers many specific examples arising from applications, including tensor regression, tensor completion, and tensor PCA/SVD. We consider an efficient Riemannian Gauss-Newton (RGN) method for low Tucker rank tensor estimation. Different from the generic (super)linear convergence guarantee of RGN in the literature, we prove the first local quadratic convergence guarantee of RGN for low-rank tensor estimation in the noisy setting under some regularity conditions and provide the corresponding estimation error upper bounds. A deterministic estimation error lower bound, which matches the upper bound, is provided that demonstrates the statistical optimality of RGN. The merit of RGN is illustrated through two machine learning applications: tensor regression and tensor SVD. Finally, we provide the simulation results to corroborate our theoretical findings.

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。

↑