PANOC-lite is a proximal-gradient linesearch method with a cheaper backtracking procedure and novel merit function that achieves global subsequential convergence and local superlinear convergence under standard assumptions.
A trust region-type normal map-based semismooth Newton method for nonsmooth nonconvex composite optimization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PANOC-lite: A simpler and more efficient algorithm for composite minimization
PANOC-lite is a proximal-gradient linesearch method with a cheaper backtracking procedure and novel merit function that achieves global subsequential convergence and local superlinear convergence under standard assumptions.