arXiv cs.LG
· Papers
Adaptive Bregman Proximal Stochastic Gradient with a Stabilized Barzilai–Borwein Step Size
arXiv:2608.12009v1 Announce Type: cross Abstract: Bregman proximal stochastic gradient (BPSG) methods bring variance-reduced composite optimization to objectives whose geometry is poorly captured by Euclidean smoothness. Their performance, however, remains sensitive to the step size: raw stochastic curvature estimates