Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo
share
Hamiltonian Monte Carlo (HMC) is a widely deployed method to sample from high-dimensional 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^1/4 steps. Here we show that this conjecture is true when sampling from strongly log-concave target distributions that satisfy a weak third-order regularity property associated with the input data. Our regularity condition is weaker than the Lipschitz Hessian property and allows us to show faster running time bounds for a much larger class of distributions than would be possible with the usual Lipschitz Hessian constant alone. Important distributions that satisfy our regularity condition include posterior distributions used in Bayesian logistic regression for which the data satisfies an "incoherence" property. Our result compares favorably with the best available running time bounds for the class of strongly log-concave distributions, which grow like d^1/2 with the dimension. Moreover, our simulations on synthetic data suggest that, when our regularity condition is satisfied, the leapfrog HMC performs better than its competitors -- both in terms of accuracy and running time.
READ FULL TEXT
