Nuclear norm minimization and semidefinite-constrained ERM achieve optimal O(rn) sample complexity for low-rank matrix recovery under heavy-tailed quadratic sampling with only finite 4+δ moments.
Bounding the smallest singular value of a random matrix without concentration.International Mathematics Re- search Notices, 2015(23):12991–13008, 2015
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Low-Rank Matrix Recovery via Heavy-Tailed Quadratic Sampling
Nuclear norm minimization and semidefinite-constrained ERM achieve optimal O(rn) sample complexity for low-rank matrix recovery under heavy-tailed quadratic sampling with only finite 4+δ moments.