Diffusion strategy for distributed learning escapes saddle points in O(1/μ) iterations and returns approximate second-order stationary points in polynomial iterations with less restrictive noise assumptions than centralized methods.
Second-o rder guaran- tees of distributed gradient algorithms,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2019 3verdicts
UNVERDICTED 3representative citing papers
A consensus + innovations algorithm with decaying additive Gaussian noise converges to the global minima of nonconvex functions under technical assumptions, with verification methods and a target-localization example.
Diffusion learning achieves linear-rate agreement around the network centroid in stochastic non-convex distributed optimization.
citing papers explorer
-
Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points
Diffusion strategy for distributed learning escapes saddle points in O(1/μ) iterations and returns approximate second-order stationary points in polynomial iterations with less restrictive noise assumptions than centralized methods.
-
Distributed Global Optimization by Annealing
A consensus + innovations algorithm with decaying additive Gaussian noise converges to the global minima of nonconvex functions under technical assumptions, with verification methods and a target-localization example.
-
Distributed Learning in Non-Convex Environments -- Part I: Agreement at a Linear Rate
Diffusion learning achieves linear-rate agreement around the network centroid in stochastic non-convex distributed optimization.