In this paper, we investigate the matrix estimation problem in the multi-response regression model with measurement errors. A nonconvex error-corrected estimator based on a combination of the amended loss function and the nuclear norm regularizer is proposed to estimate the matrix parameter. Then under the (near) low-rank assumption, we analyse statistical and computational theoretical properties of global solutions of the nonconvex regularized estimator from a general point of view. In the statistical aspect, we establish the nonasymptotic recovery bound for any global solution of the nonconvex estimator, under restricted strong convexity on the loss function. In the computational aspect, we solve the nonconvex optimization problem via the proximal gradient method. The algorithm is proved to converge to a near-global solution and achieve a linear convergence rate. In addition, we also verify sufficient conditions for the general results to be held, in order to obtain probabilistic consequences for specific types of measurement errors, including the additive noise and missing data. Finally, theoretical consequences are demonstrated by several numerical experiments on corrupted errors-in-variables multi-response regression models. Simulation results reveal excellent consistency with our theory under high-dimensional scaling.
翻译:在本文中,我们用测量错误来调查多反应回归模型中的矩阵估算问题。一个基于修正损失函数和核规范校正器的组合,基于修正损失函数和核规范校正器的不convex校正估计估计值,以估计矩阵参数。然后在(近)低位假设下,我们从总体角度分析非conex正规估算器全球解决方案的统计和计算理论性能。在统计方面,我们为非Convex估计器的任何全球解决方案设定非抽取性恢复界限,在损失函数的强稳稳状态下。在计算方面,我们通过准偏差梯度方法解决非cablex优化问题。这种算法被证明为接近全球解决方案并达到线性趋同率。此外,我们还核实了保持总体结果的充分条件,以便获得具体类型测量错误的概率性后果,包括添加噪音和缺失的数据。最后,在可变率高的理论性位模型下,通过若干项数值实验,以极强的模型显示理论性后果。