Adaptive Newton-CG methods achieve the best-known iteration complexity for epsilon-stationary points in nonconvex optimization with Holder continuous Hessians while ensuring local superlinear convergence.
Title resolution pending
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
-
Adaptive Newton-CG methods with global and local analysis for unconstrained optimization with H\"older continuous Hessian
Adaptive Newton-CG methods achieve the best-known iteration complexity for epsilon-stationary points in nonconvex optimization with Holder continuous Hessians while ensuring local superlinear convergence.