Follow
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization https://arxiv.org/abs/2406.08654 #stat.ML #math.OC #cs.LG
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization https://arxiv.org/abs/2406.08654 #stat.ML #math.OC #cs.LG