Elastic Consistency

Autor: Dan Alistarh, Ilia Markov, Giorgi Nadiradze
Rok vydání: 2022
Předmět:
Zdroj: ACM SIGACT News. 53:64-82
ISSN: 0163-5700
Popis: Machine learning models can match or surpass humans on specialized tasks such as image classification [20, 14], speech recognition [37], or complex games [39]. One key tool behind this progress has been a family of optimization methods which fall under the umbrella term of stochastic gradient descent (SGD) [35], which are by and large the method of choice for training large-scale machine learning models.
Databáze: OpenAIRE