双因子张量范数正则化低秩张量填充

Double Factor Tensor Norm Regularized Low Rank Tensor Completion

本文提出了一种新的正则化方法,解决了低秩张量恢复问题。通过将张量Schatten-p范数分解成l2,q范数与l2,1范数的加权和,避免了求解张量Schatten-p范数需要张量奇异值分解的问题,从而降低了算法的复杂度。采用交替方向乘子法用于求解提出的模型。通过真实数据的实验,在精度和时间复杂度两个方面验证了算法的有效性。

In this paper, a new regularization method is proposed to solve the recovery problem of low rank tensors. By decomposing the tensor Schatten-p norm into the weighted sum of l2,q -norm and l2,1 -norm, the problem of solving the tensor Schatten-p norm requiring tensor singular value decom-position is avoided, reducing the complexity of the algorithm. The alternating direction multiplier method is used to solve the proposed model. Experiments on real data demonstrate the effective-ness of the algorithm in terms of accuracy and time complexity.