Sheaf-ADMM trains multi-agent systems by unrolling ADMM with sheaf-specified constraints, yielding improved MNIST robustness to shifts and higher Sudoku solve rates than MPNN baselines.
Global convergence of ADMM in nonconvex nonsmooth optimization
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A new adaptive multiparameter penalty selection method for multiconstraint and multiblock ADMM provides robustness to scale differences and initial parameter choices.
Overlapping Schwarz decomposition for nonlinear OCPs achieves local linear convergence with rate improving exponentially with overlap size, based on exponential decay of sensitivity for primal and dual solutions.
citing papers explorer
-
Learning Multi-Agent Coordination via Sheaf-ADMM
Sheaf-ADMM trains multi-agent systems by unrolling ADMM with sheaf-specified constraints, yielding improved MNIST robustness to shifts and higher Sudoku solve rates than MPNN baselines.
-
An Adaptive Multiparameter Penalty Selection Method for Multiconstraint and Multiblock ADMM
A new adaptive multiparameter penalty selection method for multiconstraint and multiblock ADMM provides robustness to scale differences and initial parameter choices.
-
On the Convergence of Overlapping Schwarz Decomposition for Nonlinear Optimal Control
Overlapping Schwarz decomposition for nonlinear OCPs achieves local linear convergence with rate improving exponentially with overlap size, based on exponential decay of sensitivity for primal and dual solutions.