Adaptive Natural Gradient Method for Learning of Stochastic Neural Networks in Mini-Batch Mode
Sign Up to like & getrecommendations! Published in 2019 at "Applied Sciences"
DOI: 10.3390/app9214568
Abstract: Gradient descent method is an essential algorithm for learning of neural networks. Among diverse variations of gradient descent method that have been developed for accelerating learning speed, the natural gradient learning is based on the… read more here.
Keywords: mini batch; neural networks; method; adaptive natural ... See more keywords
Mini-Batch Stochastic Three-Operator Splitting for Distributed Optimization
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Control Systems Letters"
DOI: 10.48550/arxiv.2203.04020
Abstract: We consider a network of agents, each with its own private cost consisting of a sum of two possibly nonsmooth convex functions, one of which is composed with a linear operator. At every iteration each… read more here.
Keywords: operator; mini batch; batch stochastic; three operator ... See more keywords