GRiLS is a gradient-free MCMC proposal derived via a Lamperti transform of Riemannian Langevin dynamics, using a Gaussian approximation of the target to enable mode-hopping without gradient evaluations.
Communications in applied mathematics and computational science , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gradient-free Riemannian Langevin Sampler
GRiLS is a gradient-free MCMC proposal derived via a Lamperti transform of Riemannian Langevin dynamics, using a Gaussian approximation of the target to enable mode-hopping without gradient evaluations.