Jannis Born, Matteo Manica
ICLR 2022
We represent the abstract Hamiltonian (Hybrid) Monte Carlo (HMC) algorithm as iterations of an operator on densities in a Hilbert space, and recognize two invariant properties of Hamiltonian motion sufficient for convergence. Under a mild coverage assumption, we present a proof of strong convergence of the algorithm to the target density. The proof relies on the self-adjointness of the operator, and we extend the result to the general case of the motions beyond Hamiltonian ones acting on a finite dimensional space, to the motions acting an abstract space equipped with a reference measure, as long as they satisfy the two sufficient properties. For standard Hamiltonian motion, the convergence is also geometric in the case when the target density satisfies a log-convexity condition.
Jannis Born, Matteo Manica
ICLR 2022
Venkatesan T. Chakaravarthy, Shivmaran S. Pandian, et al.
SC 2021
Dian Balta, Mahdi Sellami, et al.
ePart 2021
Michael Feffer, Martin Hirzel, et al.
ICML 2022