Metropolis-Hastings with Levy jumps prevents entrapment in weighted random walks, yielding a convergence rate that accounts for data heterogeneity, network spectral gap, and jump probability.
Distributed subgradient methods for multi- agent optimization,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
A distributed recursive least squares algorithm achieves almost sure convergence for infinite-dimensional stochastic regression models under a cooperative excitation condition without requiring independence or stationarity of regressors.
QANM combines Nesterov-accelerated gradient descent with distributed finite-time quantized consensus to achieve linear convergence to a neighborhood of the optimum in unconstrained distributed optimization over directed graphs under strong convexity and smoothness.
A fully distributed primal-dual algorithm solves nonsmooth strongly convex problems with coupled constraints on time-varying digraphs at O(1/k) rate without communicating primal variables.
citing papers explorer
-
Decentralized Learning via Random Walk with Jumps
Metropolis-Hastings with Levy jumps prevents entrapment in weighted random walks, yielding a convergence rate that accounts for data heterogeneity, network spectral gap, and jump probability.
-
Distributed adaptive estimation for stochastic large regression models
A distributed recursive least squares algorithm achieves almost sure convergence for infinite-dimensional stochastic regression models under a cooperative excitation condition without requiring independence or stationarity of regressors.
-
Nesterov Accelerated Distributed Optimization with Efficient Quantized Communication
QANM combines Nesterov-accelerated gradient descent with distributed finite-time quantized consensus to achieve linear convergence to a neighborhood of the optimum in unconstrained distributed optimization over directed graphs under strong convexity and smoothness.
-
Distributed Optimization with Coupled Constraints over Time-Varying Digraph
A fully distributed primal-dual algorithm solves nonsmooth strongly convex problems with coupled constraints on time-varying digraphs at O(1/k) rate without communicating primal variables.