eNMF is a new exterior-point algorithm for NMF that initializes from unconstrained factorization, applies a rotation to reach the nonnegative boundary, and empirically outperforms 81 baseline combinations on real and synthetic data.
Frontiers of Mathematics in China , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Nonconvex projected gradient descent for noisy inductive matrix completion achieves linear convergence and order-optimal error at sample complexity scaling with side-information dimension a instead of ambient dimension n.
citing papers explorer
-
An Exterior Method for Nonnegative Matrix Factorization
eNMF is a new exterior-point algorithm for NMF that initializes from unconstrained factorization, applies a rotation to reach the nonnegative boundary, and empirically outperforms 81 baseline combinations on real and synthetic data.
-
Sample efficient inductive matrix completion with noise and inexact side information
Nonconvex projected gradient descent for noisy inductive matrix completion achieves linear convergence and order-optimal error at sample complexity scaling with side-information dimension a instead of ambient dimension n.