Optimal High-order Tensor SVD via Tensor-Train Orthogonal Iteration
This work addresses computational efficiency and optimal estimation for high-order tensor SVD, with applications in high-order Markov processes and real-world data like taxi records, representing a novel method for a known bottleneck.
The paper tackles the problem of estimating low tensor-train rank structures from noisy high-order tensor observations by proposing the tensor-train orthogonal iteration (TTOI) algorithm, which achieves minimax optimality under the spiked tensor model.
This paper studies a general framework for high-order tensor SVD. We propose a new computationally efficient algorithm, tensor-train orthogonal iteration (TTOI), that aims to estimate the low tensor-train rank structure from the noisy high-order tensor observation. The proposed TTOI consists of initialization via TT-SVD (Oseledets, 2011) and new iterative backward/forward updates. We develop the general upper bound on estimation error for TTOI with the support of several new representation lemmas on tensor matricizations. By developing a matching information-theoretic lower bound, we also prove that TTOI achieves the minimax optimality under the spiked tensor model. The merits of the proposed TTOI are illustrated through applications to estimation and dimension reduction of high-order Markov processes, numerical studies, and a real data example on New York City taxi travel records. The software of the proposed algorithm is available online$^6$.