A deep-unfolded distributed ADMM/OSQP solver learns penalty parameters on small QPs and solves much larger ones with large wall-clock speedups, with PAC-Bayes bounds on relative progress.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Deep Distributed Optimization for Large-Scale Quadratic Programming
A deep-unfolded distributed ADMM/OSQP solver learns penalty parameters on small QPs and solves much larger ones with large wall-clock speedups, with PAC-Bayes bounds on relative progress.