Special Issue Papers: Randomized Step Sizes and Additive Averaging Kernels for MCMC

Two new papers in a special issue on dynamical Monte Carlo cover randomized step sizes making Metropolis–Hastings more tuning-robust, and additive averaging kernels with partition optimization to speed up convergence of finite Markov chains.

2026-09-22 ~ 2026-09-22 · 2 related posts

• Randomized step sizes make Metropolis–Hastings robust to tuning, study finds — michaelchchoi · 2026-09-22
• Additive averaging kernels speed up finite Markov chains via partition optimization — michaelchchoi · 2026-09-22