2000 character limit reached
Non-asymptotic error bounds for scaled underdamped Langevin MCMC (1912.03154v1)
Published 6 Dec 2019 in stat.ML and cs.LG
Abstract: Recent works have derived non-asymptotic upper bounds for convergence of underdamped Langevin MCMC. We revisit these bound and consider introducing scaling terms in the underlying underdamped Langevin equation. In particular, we provide conditions under which an appropriate scaling allows to improve the error bounds in terms of the condition number of the underlying density of interest.