SOURCE-LINKED INTELLIGENCE

AURA: Angular Update Rate Adaptation for training complex-valued neural networks

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

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.

Read original source ↗ Open in workspace

recordType

paper

region

Global