Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo

Oren Mangoubi, Nisheeth Vishnoi

Neural Information Processing Systems 

Hamiltonian Monte Carlo (HMC) is a widely deployed method to sample from highdimensional distributions in Statistics and Machine learning. HMC is known to run very efficiently in practice and its popular second-order "leapfrog" implementation has long been conjectured to run in d