Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.00467 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910183527022592 |
|---|---|
| author | Nguyen, Xuan Son Grozavu, Nistor |
| author_facet | Nguyen, Xuan Son Grozavu, Nistor |
| contents | Riemannian neural networks have proven effective in solving a variety of machine learning tasks. The key to their success lies in the development of principled Riemannian analogs of fundamental building blocks in deep neural networks (DNNs). Among those, Riemannian batch normalization (BN) layers have shown to enhance training stability and improve accuracy. In this paper, we propose BN layers for neural networks on complex domains. The proposed layers have close connections with existing Riemannian BN layers. We derive essential components for practical implementations of BN layers on some complex domains which are less studied in previous works, e.g., the Siegel disk domain. We conduct experiments on radar clutter classification, node classification, and action recognition demonstrating the efficacy of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00467 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Batch Normalization for Neural Networks on Complex Domains Nguyen, Xuan Son Grozavu, Nistor Machine Learning Riemannian neural networks have proven effective in solving a variety of machine learning tasks. The key to their success lies in the development of principled Riemannian analogs of fundamental building blocks in deep neural networks (DNNs). Among those, Riemannian batch normalization (BN) layers have shown to enhance training stability and improve accuracy. In this paper, we propose BN layers for neural networks on complex domains. The proposed layers have close connections with existing Riemannian BN layers. We derive essential components for practical implementations of BN layers on some complex domains which are less studied in previous works, e.g., the Siegel disk domain. We conduct experiments on radar clutter classification, node classification, and action recognition demonstrating the efficacy of our method. |
| title | Batch Normalization for Neural Networks on Complex Domains |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.00467 |