A GNN is trained to predict adaptive step sizes and weights for distributed ADMM by unrolling a fixed number of iterations and minimizing solution error on a problem class.
A mathematics- inspired learning-to-optimize framework for decentralized opti- mization,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
LRMC is a deep-unfolded non-convex algorithm for large-scale robust matrix completion that learns its parameters for linear convergence and better empirical results than prior methods.
citing papers explorer
-
Learning to accelerate distributed ADMM using graph neural networks
A GNN is trained to predict adaptive step sizes and weights for distributed ADMM by unrolling a fixed number of iterations and minimizing solution error on a problem class.
-
Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery
LRMC is a deep-unfolded non-convex algorithm for large-scale robust matrix completion that learns its parameters for linear convergence and better empirical results than prior methods.