Showing 2026Show all
2 papers · 1 filter
math.OC2026
Wasserstein accelerated proximal gradient algorithms
Kansei Ushiyama, Yi Feng, Kaito Fujii +2
We propose accelerated proximal gradient methods for composite optimization problems on the quadratic Wasserstein space of probability measures, including Kullback--Leibler diverge…
math.OC2026
A restart-free accelerated algorithm for nonconvex minimization: continuous- and discrete-time analysis
Kansei Ushiyama, Shun Sato
We propose two deterministic momentum-based first-order methods for minimizing lower-bounded nonconvex functions with Lipschitz-continuous gradients and Hessians. Both methods atta…