Z-Error Loss for Training Neural Networks
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916774506659840 |
|---|---|
| author | Godin, Guillaume |
| author_facet | Godin, Guillaume |
| contents | Outliers introduce significant training challenges in neural networks by propagating erroneous gradients, which can degrade model performance and generalization. We propose the Z-Error Loss, a statistically principled approach that minimizes outlier influence during training by masking the contribution of data points identified as out-of-distribution within each batch. This method leverages batch-level statistics to automatically detect and exclude anomalous samples, allowing the model to focus its learning on the true underlying data structure. Our approach is robust, adaptive to data quality, and provides valuable diagnostics for data curation and cleaning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02154 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Z-Error Loss for Training Neural Networks Godin, Guillaume Machine Learning Artificial Intelligence Outliers introduce significant training challenges in neural networks by propagating erroneous gradients, which can degrade model performance and generalization. We propose the Z-Error Loss, a statistically principled approach that minimizes outlier influence during training by masking the contribution of data points identified as out-of-distribution within each batch. This method leverages batch-level statistics to automatically detect and exclude anomalous samples, allowing the model to focus its learning on the true underlying data structure. Our approach is robust, adaptive to data quality, and provides valuable diagnostics for data curation and cleaning. |
| title | Z-Error Loss for Training Neural Networks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.02154 |