arXiv stat.ML
· Papers
Dangerous Liaisons of Convex Learning and Non-Affine Aggregation
arXiv:2606.28123v1 Announce Type: cross Abstract: Last-iterate convergence and generalization guarantees in first-order convex learning hinge on the monotonicity of the update operator. While linear averaging preserves the monotonicity of gradient updates, this property is often violated when gradients are aggregated n