A trust-region method for nonsmooth composite optimization gets worst-case complexity bounds matching the smooth case under unbounded Hessian growth, and a new projected proximal-gradient subproblem solver is introduced.
Burke and Abraham Engle
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
-
Projected proximal gradient trust-region algorithm for nonsmooth optimization
A trust-region method for nonsmooth composite optimization gets worst-case complexity bounds matching the smooth case under unbounded Hessian growth, and a new projected proximal-gradient subproblem solver is introduced.