Diagonal plus Low-Rank (DLoR) neural networks achieve universal approximation for general activations by additive or multiplicative decompositions of full-rank transformations.
Implicit regularization in deep matrix factorization.Advances in Neural Information Processing Systems, 32, 2019
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks
Diagonal plus Low-Rank (DLoR) neural networks achieve universal approximation for general activations by additive or multiplicative decompositions of full-rank transformations.
-
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.