A truncated-SVD-plus-rounding algorithm achieves exact recovery of noisy low-rank matrices under only low rank, incoherence, and sufficient sampling, with a new infinity-norm perturbation theorem.
Bandeira and Ramon van Handel, Sharp nonasymptotic bounds on the norm of random matrices with independent entries , Ann
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.ST 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Fast exact recovery of noisy matrix from few entries: the infinity norm approach
A truncated-SVD-plus-rounding algorithm achieves exact recovery of noisy low-rank matrices under only low rank, incoherence, and sufficient sampling, with a new infinity-norm perturbation theorem.