Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time.
Yuyang DengMehrdad MahdaviPublished in: CoRR (2021)
Keyphrases
- neural network
- pattern recognition
- artificial neural networks
- special case
- genetic algorithm
- computational complexity
- self organizing maps
- fuzzy logic
- multi layer perceptron
- approximation algorithms
- multilayer perceptron
- data sets
- back propagation
- neural nets
- recurrent neural networks
- neural network model
- worst case
- np hard
- fault diagnosis
- decision trees
- fuzzy systems
- feature selection
- finite automata
- stochastic gradient descent