Non-asymptotic error bounds for scaled underdamped Langevin MCMC
arXiv:1912.03154v12 citations
Originality Synthesis-oriented
AI Analysis
This work addresses convergence analysis for MCMC methods, which is incremental as it builds on existing bounds by incorporating scaling.
The paper tackles the problem of improving non-asymptotic error bounds for underdamped Langevin MCMC by introducing scaling terms, resulting in enhanced bounds related to the condition number of the target density.
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.