Nonconvex low-rank matrix estimation procedures are shown to be equivalent to locally strongly convex formulations via a benign regularizer that does not change the algorithm's update rule.
Galore: Memory-efficient LLM training by gradient low-rank projection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Convexity in Disguise: A Theoretical Framework for Nonconvex Low-Rank Matrix Estimation
Nonconvex low-rank matrix estimation procedures are shown to be equivalent to locally strongly convex formulations via a benign regularizer that does not change the algorithm's update rule.