AI RESEARCH
Complex SGD and Directional Bias in Reproducing Kernel Hilbert Spaces
arXiv CS.LG
•
ArXi:2604.23017v1 Announce Type: new Stochastic Gradient Descent (SGD) is a known stochastic iterative method popular for large-scale convex optimization problems due to its simple implementation and scalability. Some objectives, such as those found in complex-valued neural networks, benefit from updates like in SGD and Gradient Descent (GD) with a newly defined ``gradient'' that allows for complex parameters. This complex variant of the SGD/GD methods has already been proposed, but convergence guarantees without analyticity constraints have not yet been provided.