Tensor SVD: Statistical and Computational Limits
نویسندگان
چکیده
منابع مشابه
Statistical limits of spiked tensor models
We study the statistical limits of both detecting and estimating a rank-one deformation of a symmetric random Gaussian tensor. We establish upper and lower bounds on the critical signal-to-noise ratio, under a variety of priors for the planted vector: (i) a uniformly sampled unit vector, (ii) i.i.d. ±1 entries, and (iii) a sparse vector where a constant fraction ρ of entries are i.i.d. ±1 and t...
متن کاملTensor SVD and distributed control
The (approximate) diagonalization of symmetric matrices has been studied in the past in the context of distributed control of an array of collocated smart actuators and sensors. For distributed control using a two dimensional array of actuators and sensors, it is more natural to describe the system transfer function as a complex tensor rather than a complex matrix. In this paper, we study the p...
متن کاملStatistical and Computational Limits for Sparse Matrix Detection
This paper investigates the fundamental limits for detecting a high-dimensional sparse matrix contaminated by white Gaussian noise from both the statistical and computational perspectives. We consider p×pmatrices whose rows and columns are individually k-sparse. We provide a tight characterization of the statistical and computational limits for sparse matrix detection, which precisely describe ...
متن کاملSVD compression, unitary transforms, and computational complexity
The search for fast unitary transforms and the need for data compression in linear systems are complementary issues. Compression requires the definition of a threshold dependent on the condition number, which is invariant over the unitary group. With respect tot this threshold it is shown that the SVD is the optimal tool. Considerations in connection with the Kronecker product and direct sum of...
متن کاملLow-rank Tensor Standard Forms and Limits∗
Abstract. Despite the growing use of tensor-based methods, tensors remain mysterious and misunderstood objects. In this work we develop a standard form for low-rank tensors that allows one to focus on the important defining parameters (internal angles and comparative sizes) while ignoring unimportant parameters (separable unitary transformations). This standard form eases the analysis of tensor...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Information Theory
سال: 2018
ISSN: 0018-9448,1557-9654
DOI: 10.1109/tit.2018.2841377