ASRL:A robust loss function with potential for development
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_ | 1866908309804548096 |
|---|---|
| author | Hui, Chenyu Zhang, Anran Li, Xintong |
| author_facet | Hui, Chenyu Zhang, Anran Li, Xintong |
| contents | In this article, we proposed a partition:wise robust loss function based on the previous robust loss function. The characteristics of this loss function are that it achieves high robustness and a wide range of applicability through partition-wise design and adaptive parameter adjustment. Finally, the advantages and development potential of this loss function were verified by applying this loss function to the regression question and using five different datasets (with different dimensions, different sample numbers, and different fields) to compare with the other loss functions. The results of multiple experiments have proven the advantages of our loss function . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06935 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ASRL:A robust loss function with potential for development Hui, Chenyu Zhang, Anran Li, Xintong Machine Learning In this article, we proposed a partition:wise robust loss function based on the previous robust loss function. The characteristics of this loss function are that it achieves high robustness and a wide range of applicability through partition-wise design and adaptive parameter adjustment. Finally, the advantages and development potential of this loss function were verified by applying this loss function to the regression question and using five different datasets (with different dimensions, different sample numbers, and different fields) to compare with the other loss functions. The results of multiple experiments have proven the advantages of our loss function . |
| title | ASRL:A robust loss function with potential for development |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.06935 |