Derives linear sample complexity for PDHG parameters and polynomial sample complexity for full PDLP hyperparameters using data-driven algorithm design.
An overview of GPU-based first-order methods for linear programming and extensions.arXiv preprint arXiv:2506.02174, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.OC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Parameter Tuning with Generalization Guarantees for GPU-Accelerated Linear Programming
Derives linear sample complexity for PDHG parameters and polynomial sample complexity for full PDLP hyperparameters using data-driven algorithm design.
-
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.