Jul 2026
Tamed Stochastic Gradient Hamiltonian Monte Carlo
A novel tamed stochastic gradient Hamiltonian Monte Carlo algorithm for sampling and stochastic optimization problems with superlinearly growing stochastic gradients is proposed, which achieves lower root mean square error and expected excess risk across a range of tasks.
Zhu-Ding Wang, Ying Zhang
· arXiv.org · 0 citations