Discrete Hyperparameter Optimization Model Based on Skewed Distribution

As for the machine learning algorithm, one of the main factors restricting its further large-scale application is the value of hyperparameter. Therefore, researchers have done a lot of original numerical optimization algorithms to ensure the validity of hyperparameter selection. Based on previous st...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Mathematical problems in engineering Ročník 2022; s. 1 - 10
Hlavný autor: Li, Yuqi
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Hindawi 09.08.2022
John Wiley & Sons, Inc
Predmet:
Algorithms
Consumer behavior
Consumers
Datasets
Engineering
Experiments
Hypergeometric functions
Machine learning
Optimization models
Parameters
Probability distribution
Probability distribution functions
Skewed distributions
ISSN:1024-123X, 1563-5147
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:As for the machine learning algorithm, one of the main factors restricting its further large-scale application is the value of hyperparameter. Therefore, researchers have done a lot of original numerical optimization algorithms to ensure the validity of hyperparameter selection. Based on previous studies, this study innovatively puts forward a model generated using skewed distribution (gamma distribution) as hyperparameter fitting and combines the Bayesian estimation method and Gauss hypergeometric function to propose a mathematically optimal solution for discrete hyperparameter selection. The results show that under strict mathematical conditions, the value of discrete hyperparameters can be given a reasonable expected value. This heuristic parameter adjustment method based on prior conditions can improve the accuracy of some traditional models in experiments and then improve the application value of models. At the same time, through the empirical study of relevant datasets, the effectiveness of the parameter adjustment strategy proposed in this study is further proved.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1024-123X
1563-5147
DOI:10.1155/2022/2835596