Near-optimal sample complexity for convex tensor completion

DOI10.1093/IMAIAI/IAY019MaRDI QIDQ5006503zbMATH OpenOpenAlexWikidataFDO

Authors Navid Ghadermarzy, Özgür Yılmaz, Y. Plan

Publication date 16 August 2021

Published in Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1711.04965

zbMATH Keywords

compressed sensinglow-rank tensorm-norm constrained tensor completionmatrix completionmax normRademacher complexitytensor completion

Mathematics Subject Classification ID

Convex programming (90C25) Nonlinear programming (90C30)

Recommendations

• Tensor completion and low-\(n\)-rank tensor recovery via convex optimization
• Hypercomplex Tensor Completion via Convex Optimization
• Tensor Completion From Regular Sub-Nyquist Samples
• On polynomial time methods for exact low-rank tensor completion
• A non-convex tensor rank approximation for tensor completion
• Nonconvex optimization for robust tensor completion from grossly sparse observations
• On tensor completion via nuclear norm minimization
• Convex coupled matrix and tensor completion
• Exact Tensor Completion Using t-SVD
• Robust tensor completion: equivalent surrogates, error bounds, and algorithms

Cited in

(6)

• Tensor completion based on triple tubal nuclear norm
• Deterministic tensor completion with hypergraph expanders
• When big data actually are low-rank, or entrywise approximation of certain function-generated matrices
• Entrywise tensor-train approximation of large tensors via random embeddings
• Robust tensor completion from uniformly dithered one-bit observations
• Identifiability of points and rigidity of hypergraphs under algebraic constraints

This page was built for publication: Near-optimal sample complexity for convex tensor completion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5006503)