Develops restarted accelerated primal-dual methods with monotone and non-monotone adaptive stepsizes that achieve global linear convergence for nonlinear conic convex programs under metric subregularity of the KKT mapping.
A technical note on the implementation and use of PDCS.arXiv:2603.15504, 2026
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
-
Restarted Accelerated Primal-Dual Algorithms with Adaptive Stepsizes for Nonlinear Conic Constrained Convex Optimization
Develops restarted accelerated primal-dual methods with monotone and non-monotone adaptive stepsizes that achieve global linear convergence for nonlinear conic convex programs under metric subregularity of the KKT mapping.