AINeutralarXiv – CS AI · 6h ago6/10
🧠
Stochastic convergence of parallel asynchronous adaptive first-order methods
Researchers introduce a new class of asynchronous adaptive first-order optimization methods that improve upon existing algorithms through momentum and inexact normalization variants. The methods achieve O(1/√t) convergence rates in stochastic non-convex settings and demonstrate practical relevance for large-scale heterogeneous machine learning systems.