论文信息 - On the extension of trace norm to tensors

On the extension of trace norm to tensors

In this paper, we propose three extensions of trace norm for the minimization of tensor rank via convex optimization. One of the proposed extensions recovers partially observed tensor almost perfectly from a small fraction of observations.

Ryota Tomioka | H. Kashima | K. Hayashi

[1] B. Mercier,et al. A dual algorithm for the solution of nonlinear variational problems via finite element approximation , 1976 .

[2] Rasmus Bro,et al. The N-way Toolbox for MATLAB , 2000 .

[3] Stephen P. Boyd,et al. Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[4] Jieping Ye,et al. Tensor Completion for Estimating Missing Values in Visual Data , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5] Tamara G. Kolda,et al. Tensor Decompositions and Applications , 2009, SIAM Rev..

[6] Pablo A. Parrilo,et al. Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization , 2007, SIAM Rev..

[7] Emmanuel J. Candès,et al. Exact Matrix Completion via Convex Optimization , 2008, Found. Comput. Math..