Conditional updates of neural network weights for increased out of training performance
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_ | 1866912746192240640 |
|---|---|
| author | Saynisch-Wagner, Jan Sari, Saran Rajendran |
| author_facet | Saynisch-Wagner, Jan Sari, Saran Rajendran |
| contents | This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main steps: 1) Retrain the neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. 2) Choose reasonable predictors and derive a regression between the predictors and the weight anomalies. 3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three use cases from the climate sciences, which include successful temporal, spatial and cross-domain extrapolations of neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03653 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Conditional updates of neural network weights for increased out of training performance Saynisch-Wagner, Jan Sari, Saran Rajendran Machine Learning Atmospheric and Oceanic Physics Data Analysis, Statistics and Probability This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main steps: 1) Retrain the neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. 2) Choose reasonable predictors and derive a regression between the predictors and the weight anomalies. 3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three use cases from the climate sciences, which include successful temporal, spatial and cross-domain extrapolations of neural networks. |
| title | Conditional updates of neural network weights for increased out of training performance |
| topic | Machine Learning Atmospheric and Oceanic Physics Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2512.03653 |