A unified zeroth-order proximal Newton framework for composite optimization establishes iteration and oracle complexity bounds for epsilon-optimality in nonconvex and strongly convex cases, proves local R-superlinear convergence, and shows BFGS is more compatible with finite-difference estimators.
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
-
A Unified Zeroth-Order Proximal Newton-Type Framework for Composite Optimization
A unified zeroth-order proximal Newton framework for composite optimization establishes iteration and oracle complexity bounds for epsilon-optimality in nonconvex and strongly convex cases, proves local R-superlinear convergence, and shows BFGS is more compatible with finite-difference estimators.