Showing 2026Show all
2 papers · 1 filter
math.OC2026
Convergence of Riemannian Stochastic Gradient Descents: Varying Batch Sizes And Nonstandard Batch Forming
Hao Wu
We establish convergence theorems for Riemannian stochastic gradient descents in which the underlying probability spaces vary from iteration to iteration. As applications, we deduc…
math.DG2026
Bauer-Furuta invariants
Hao Wu
Adapting Bauer and Furuta's constructions of the refinement of the Seiberg-Witten invariants, we establish the analogous stable cohomotopy refinement of the monopole i…