Automated Machine Learning: Advances in Model Selection and Hyperparameter Optimization

EasyChair Preprint no. 12355

Abstract

This paper presents recent advances in AutoML, focusing on techniques for selecting models and tuning hyperparameters efficiently and effectively. Various approaches, including Bayesian optimization, genetic algorithms, and neural architecture search, are explored for automating these tasks. Moreover, the challenges and opportunities associated with adopting AutoML are discussed, including scalability, interpretability, and computational resource requirements. Finally, future research directions and potential applications of AutoML in accelerating the development and deployment of machine learning models across diverse domains are highlighted.

Keyphrases: Hyperparameter, model, selection

@Booklet{EasyChair:12355,
  author = {Julia Anderson and Jane Smith},
  title = {Automated Machine Learning: Advances in Model Selection and Hyperparameter Optimization},
  howpublished = {EasyChair Preprint no. 12355},

  year = {EasyChair, 2024}}