Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models

We present dimension-free convergence and discretization error bounds for the unadjusted Hamiltonian Monte Carlo algorithm applied to high-dimensional probability distributions of mean-field type. These require step be sufficiently small, but do not strong convexity either unary or pairwise potential terms in model. To handle high dimensionality, our proof uses a particlewise coupling that is contractive complementary metric.