A survey and taxonomy of loss functions in machine learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912121053249536 |
|---|---|
| author | Ciampiconi, Lorenzo Elwood, Adam Leonardi, Marco Mohamed, Ashraf Rozza, Alessandro |
| author_facet | Ciampiconi, Lorenzo Elwood, Adam Leonardi, Marco Mohamed, Ashraf Rozza, Alessandro |
| contents | Most state-of-the-art machine learning techniques revolve around the optimisation of loss functions. Defining appropriate loss functions is therefore critical to successfully solving problems in this field. In this survey, we present a comprehensive overview of the most widely used loss functions across key applications, including regression, classification, generative modeling, ranking, and energy-based modeling. We introduce 43 distinct loss functions, structured within an intuitive taxonomy that clarifies their theoretical foundations, properties, and optimal application contexts. This survey is intended as a resource for undergraduate, graduate, and Ph.D. students, as well as researchers seeking a deeper understanding of loss functions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_05579 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A survey and taxonomy of loss functions in machine learning Ciampiconi, Lorenzo Elwood, Adam Leonardi, Marco Mohamed, Ashraf Rozza, Alessandro Machine Learning Most state-of-the-art machine learning techniques revolve around the optimisation of loss functions. Defining appropriate loss functions is therefore critical to successfully solving problems in this field. In this survey, we present a comprehensive overview of the most widely used loss functions across key applications, including regression, classification, generative modeling, ranking, and energy-based modeling. We introduce 43 distinct loss functions, structured within an intuitive taxonomy that clarifies their theoretical foundations, properties, and optimal application contexts. This survey is intended as a resource for undergraduate, graduate, and Ph.D. students, as well as researchers seeking a deeper understanding of loss functions. |
| title | A survey and taxonomy of loss functions in machine learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2301.05579 |