Mind the Gap: Measuring Generalization Performance Across Multiple Objectives
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929258089152512 |
|---|---|
| author | Feurer, Matthias Eggensperger, Katharina Bergman, Edward Pfisterer, Florian Bischl, Bernd Hutter, Frank |
| author_facet | Feurer, Matthias Eggensperger, Katharina Bergman, Edward Pfisterer, Florian Bischl, Bernd Hutter, Frank |
| contents | Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such candidate models, and the approximation of the Pareto front is used to assess their performance. In practice, we also want to measure generalization when moving from the validation to the test set. However, some of the models might no longer be Pareto-optimal which makes it unclear how to quantify the performance of the MHPO method when evaluated on the test set. To resolve this, we provide a novel evaluation protocol that allows measuring the generalization performance of MHPO methods and studying its capabilities for comparing two optimization experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_04183 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Mind the Gap: Measuring Generalization Performance Across Multiple Objectives Feurer, Matthias Eggensperger, Katharina Bergman, Edward Pfisterer, Florian Bischl, Bernd Hutter, Frank Machine Learning Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such candidate models, and the approximation of the Pareto front is used to assess their performance. In practice, we also want to measure generalization when moving from the validation to the test set. However, some of the models might no longer be Pareto-optimal which makes it unclear how to quantify the performance of the MHPO method when evaluated on the test set. To resolve this, we provide a novel evaluation protocol that allows measuring the generalization performance of MHPO methods and studying its capabilities for comparing two optimization experiments. |
| title | Mind the Gap: Measuring Generalization Performance Across Multiple Objectives |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2212.04183 |