Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908664208556032 |
|---|---|
| author | Balef, Amir Rezaei Vernade, Claire Eggensperger, Katharina |
| author_facet | Balef, Amir Rezaei Vernade, Claire Eggensperger, Katharina |
| contents | The Combined Algorithm Selection and Hyperparameter optimization (CASH) is a challenging resource allocation problem in the field of AutoML. We propose MaxUCB, a max k-armed bandit method to trade off exploring different model classes and conducting hyperparameter optimization. MaxUCB is specifically designed for the light-tailed and bounded reward distributions arising in this setting and, thus, provides an efficient alternative compared to classic max k-armed bandit methods assuming heavy-tailed reward distributions. We theoretically and empirically evaluate our method on four standard AutoML benchmarks, demonstrating superior performance over prior approaches. We make our code and data available at https://github.com/amirbalef/CASH_with_Bandits |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05226 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning Balef, Amir Rezaei Vernade, Claire Eggensperger, Katharina Machine Learning Artificial Intelligence The Combined Algorithm Selection and Hyperparameter optimization (CASH) is a challenging resource allocation problem in the field of AutoML. We propose MaxUCB, a max k-armed bandit method to trade off exploring different model classes and conducting hyperparameter optimization. MaxUCB is specifically designed for the light-tailed and bounded reward distributions arising in this setting and, thus, provides an efficient alternative compared to classic max k-armed bandit methods assuming heavy-tailed reward distributions. We theoretically and empirically evaluate our method on four standard AutoML benchmarks, demonstrating superior performance over prior approaches. We make our code and data available at https://github.com/amirbalef/CASH_with_Bandits |
| title | Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.05226 |