Metraipolis › archive › dc_21650647ce69
AURA: Angular Update Rate Adaptation for training complex-valued neural networks — arXiv:2609.25914
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25914
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T15:07:36.560Z
- SHA-256 of the archived text
360b70e8616f8689085c44ee2903b0cc159a37878e96dbc95843be9e14423dbf- Stable URL of this page
https://metraipolis.com/documento/dc_21650647ce69
How to cite
AURA: Angular Update Rate Adaptation for training complex-valued neural networks — arXiv:2609.25914 — arXiv (en), https://arxiv.org/abs/2609.25914 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_21650647ce69 (Metraipolis archive dc_21650647ce69, sha256 360b70e8616f8689085c44ee2903b0cc159a37878e96dbc95843be9e14423dbf)
BibTeX
@misc{dc21650647ce69,
title = {AURA: Angular Update Rate Adaptation for training complex-valued neural networks — arXiv:2609.25914},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25914},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_21650647ce69; sha256 360b70e8616f8689085c44ee2903b0cc159a37878e96dbc95843be9e14423dbf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25914. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Complex-valued neural networks (CVNNs) are increasingly adopted for complex-valued data; however, they are often trained with first-order optimizers inherited from the real-valued case. The efficiency of these methods depends largely on the step size, and their step-size rules ignore the angular information available in the complex plane. We address step-size adaptation in the complex domain by introducing AURA (Angular Update Rate Adaptation), a per-parameter step-size adaptation that can be added on top of any first-order optimizer, and removed from it, without altering its update direction. AURA measures the agreement between consecutive updates of each complex parameter, in length, alignment, and sense of rotation, and enlarges the step when they are consistent and reduces it when they are not. It requires no additional gradient evaluations and only inexpensive vector operations per step. We combine AURA with Adam and Muon and compare the resulting methods with well-known first-order optimizers on four test cases of increasing complexity, ranging from the approximation of scalar complex functions to physics-informed training. Fully connected neural networks are used throughout this work. All hyperparameters other than the step size are held fixed across test cases; for one case, we also tune the hyperparameters of each optimizer under the same budget. Our empirical tests show that AURA improves the convergence of its base optimizer in most cases with a small per-step overhead, and we identify the conditions under which it fails to do so. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Numerical Analysis (math.NA). Pagina del lavoro: https://arxiv.org/abs/2609.25914 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T14:37:29.439Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).