Tensor train completion: Local recovery guarantees via Riemannian optimization

DOI10.1002/NLA.2520MaRDI QIDQ6137140zbMATH OpenOpenAlexFDO

Authors Stanislav S. Budzinskiy, N. L. Zamarashkin

Publication date 18 January 2024

Published in Numerical Linear Algebra with Applications (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2110.03975

zbMATH Keywords

incoherenceRiemannian optimizationsubspace informationtensor completiontensor traintensors

Mathematics Subject Classification ID

Multilinear algebra, tensor calculus (15A69) Numerical methods for low-rank matrix approximation; matrix compression (65F55)

Abstract: In this work we estimate the number of randomly selected elements of a tensor that with high probability guarantees local convergence of Riemannian gradient descent for tensor train completion. We derive a new bound for the orthogonal projections onto the tangent spaces based on the harmonic mean of the unfoldings' singular values and introduce a notion of core coherence for tensor trains. We also extend the results to tensor train completion with side information and obtain the corresponding local convergence guarantees.

Cited in

(3)

• Variational Bayesian inference for CP tensor completion with subspace information
• Quasioptimal alternating projections and their use in low-rank approximation of matrices and tensors
• Entrywise tensor-train approximation of large tensors via random embeddings

This page was built for publication: Tensor train completion: Local recovery guarantees via Riemannian optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6137140)