cs.LG, cs.NA, math.CV, math.NA

Complex SGD and Directional Bias in Reproducing Kernel Hilbert Spaces

arXiv:2604.23017v1 Announce Type: new
Abstract: 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 th…