AURA: Angular Update Rate Adaptation for training complex-valued neural networks
cs.LG, cs.NA, math.NA
Submitted: 2026-09-22
Updated: 2026-09-22
Code: https://github.com/enricoballini/aura
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks
- ADADELTA: An Adaptive Learning Rate Method
- Adam: A Method for Stochastic Optimization
- Adaptive Gradient Method with Resilience and Momentum
- Torque-Aware Momentum
- A holomorphic neural network framework for 3D boundary value problems governed by harmonic potentials
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks