arXiv stat.ML
· Papers
Born Discrete, Made Smooth: Variational Formulation of Shallow Neural Networks
arXiv:2607.02003v1 Announce Type: new Abstract: Although neural networks are remarkably effective, their underlying optimization principles remain theoretically elusive, often characterized by non-convex landscapes and stochastic heuristics. In this work, we propose a paradigm shift by replacing the discrete training p