A Malliavin-calculus Girsanov analysis yields process-level KL and Rényi bounds for midpoint Langevin discretizations and a O~(kappa^{5/4} d^{1/4}/epsilon^{1/2}) query complexity for a new deterministic double midpoint sampler.
Stochastic Runge–Kutta accelerates Langevin Monte Carlo and beyond
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Analysis of Langevin midpoint methods using an anticipative Girsanov theorem
A Malliavin-calculus Girsanov analysis yields process-level KL and Rényi bounds for midpoint Langevin discretizations and a O~(kappa^{5/4} d^{1/4}/epsilon^{1/2}) query complexity for a new deterministic double midpoint sampler.