kTULA achieves a non-asymptotic KL convergence of order lambda^(2-epsilon) for non-log-concave targets with super-linear log-gradients under a Log-Sobolev inequality, improving prior order-lambda KL bounds.
The tamed unadjusted Langevin algorithm.Stochastic Processes and their Applications, 129(10):3638–3663, 2019
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.ST 1years
2025 1verdicts
ACCEPT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients
kTULA achieves a non-asymptotic KL convergence of order lambda^(2-epsilon) for non-log-concave targets with super-linear log-gradients under a Log-Sobolev inequality, improving prior order-lambda KL bounds.