A Newton-type method for box-constrained ℓ0-regularized optimization is shown to converge globally and quadratically near a strict local minimizer.
IEEE transactions on neural networks and learning systems 23(3), 399–411 (2012)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Subspace Newton's Method for $\ell_0$-Regularized Optimization Problems with Box Constraint
A Newton-type method for box-constrained ℓ0-regularized optimization is shown to converge globally and quadratically near a strict local minimizer.