2 papers
math.NA2026
On the computational cost of Stochastic Gradient Langevin Dynamics
Mateusz B. Majka, Tigran Nagapetyan, Łukasz Szpruch +2
Stochastic Gradient Langevin Dynamics (SGLD) reduces the cost of Langevin-based sampling by replacing full-dataset drift evaluations with mini-batch approximations, but the resulti…
cs.CV2026
PTL-Diffusion: Manifold-Aware Diffusion with Periodic Terminal Laws
Danqi Zhuang, Jisui Huang, Xiaoyue Xi +4
Standard diffusion models typically use a single time-homogeneous Gaussian terminal distribution as the reference law for generation. While this choice is analytically convenient a…