A nonconvex l1/2-regularized nonnegative matrix factorization method with ADMM solver and detection estimation improves sparse network recovery under imperfect observations compared to baselines.
Convergence analysis of alternating direction method of multipliers for a family of nonconvex problems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces Full-Covariance-Consensus, Partial-Covariance-Consensus, and Mean-Consensus distributed covariance steering methods via non-convex ADMM, with convergence guarantees for the latter two and demonstrations of scalability to thousands of agents.
citing papers explorer
-
Sparse Network Inference under Imperfect Detection and its Application to Ecological Networks
A nonconvex l1/2-regularized nonnegative matrix factorization method with ADMM solver and detection estimation improves sparse network recovery under imperfect observations compared to baselines.
-
Distributed Covariance Steering via Non-Convex ADMM for Large-Scale Multi-Agent Systems
Introduces Full-Covariance-Consensus, Partial-Covariance-Consensus, and Mean-Consensus distributed covariance steering methods via non-convex ADMM, with convergence guarantees for the latter two and demonstrations of scalability to thousands of agents.