Operator Norm Inequalities between Tensor Unfoldings on the Partition Lattice

Abstract

Interest in higher-order tensors has recently surged in data-intensive fields, with a wide range of applications including image processing, blind source separation, community detection, and feature extraction. A common paradigm in tensor-related algorithms advocates unfolding (or flattening) the tensor into a matrix and applying classical methods developed for matrices. Despite the popularity of such techniques, how the functional properties of a tensor changes upon unfolding is currently not well understood. In contrast to the body of existing work which has focused almost exclusively on matricizations, we here consider all possible unfoldings of an order-$k$ tensor, which are in one-to-one correspondence with the set of partitions of $\{1,\dots ,k\}$. We derive general inequalities between the $l^p$-norms of arbitrary unfoldings defined on the partition lattice. In particular, we demonstrate how the spectral norm ($p=2$) of a tensor is bounded by that of its unfoldings, and obtain an improved upper bound on the ratio of the Frobenius norm to the spectral norm of an arbitrary tensor. For specially-structured tensors satisfying a generalized definition of orthogonal decomposability, we prove that the spectral norm remains invariant under specific subsets of unfolding operations.

17 pages, 1 figure

References in corpus (5)

• Proceedings of the 29th International Conference on Machine Learning (ICML-12)
• Multilinear tensor regression for longitudinal relational data
• A statistical model for tensor PCA
• Tensor Factorization via Matrix Factorization
• Tensor Decompositions via Two-Mode Higher-Order SVD (HOSVD)

Cited by in corpus (9)

• Tensor Decompositions via Two-Mode Higher-Order SVD (HOSVD)
• Optimization Landscape of Tucker Decomposition
• Learning from Binary Multiway Data: Probabilistic Tensor Decomposition and its Statistical Optimality
• Sparse random tensors: Concentration, regularization and applications
• Lower bounds on the rank and symmetric rank of real tensors
• New Edgeworth-type expansions with finite sample guarantees
• Tensor denoising and completion based on ordinal observations
• Entrywise tensor-train approximation of large tensors via random embeddings
• The Tensor Track VII: From Quantum Gravity to Artificial Intelligence