2 papers
stat.CO2026
Faster Hamiltonian Monte Carlo by Learning Leapfrog Scale: a self-calibrated randomized solution
Changye Wu, Pierre Pudlo, Christian P. Robert +1
We introduce a Hamiltonian Monte Carlo (HMC) methodology based on a randomized selection of integration times, referred to as eHMC, where "e" stands for empirical. The approach rel…
stat.CO2026
Optimal Sampling for Kernel Quadrature on Unbounded Domains
Edoardo Bandoni, Christian Robert, Julien Stoehr
Kernel quadrature is widely used to approximate integrals of smooth functions, with worst-case error typically decaying at the minimax rate for smoothness in dimen…