1 citations · 1 across the 9 of their papers we have counts for
Showing 2023 · math.PRShow all
2 papers · 2 filters
math.PR2023
Convergence Of The Unadjusted Langevin Algorithm For Discontinuous Gradients
Tim Johnston, Sotirios Sabanis
We demonstrate that for strongly log-convex densities whose potentials are discontinuous on manifolds, the ULA algorithm converges with stepsize bias of order in Wasserstein-…
math.PR2023
Kinetic Langevin MCMC Sampling Without Gradient Lipschitz Continuity -- the Strongly Convex Case
Tim Johnston, Iosif Lytras, Sotirios Sabanis
In this article we consider sampling from log concave distributions in Hamiltonian setting, without assuming that the objective gradient is globally Lipschitz. We propose two algor…