Learned online policies for the ADMM relaxation parameter improve iteration count and runtime on benchmark quadratic programs while maintaining convergence guarantees for time-varying parameters under mild assumptions.
The degenerate variable metric proximal point algorithm and adaptive stepsizes for primal– dual Douglas–Rachford,
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
-
Learning Over-Relaxation Policies for ADMM with Convergence Guarantees
Learned online policies for the ADMM relaxation parameter improve iteration count and runtime on benchmark quadratic programs while maintaining convergence guarantees for time-varying parameters under mild assumptions.