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.
Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.