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 learning in non-c onvex environments – Part I: Agreement at a Linear rate,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
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.