5 papers
Wasserstein mixing time of the unadjusted Langevin algorithm
Francesco Pedrotti, Peter A. Whalley
We provide new estimates in Wasserstein distance for the asymptotic bias of the unadjusted Langevin algorithm, in the classical setting of log-smooth strongly log-concave measures.…
Accelerated sampling using SamAdams variable timesteps and position-adaptive Langevin dynamics
Benedict Leimkuhler, Peter A. Whalley
We introduce an accelerated Langevin-based sampling method that is based on two complementary devices: \emph{SamAdams} adaptive timestepping, which automatically shrinks the effect…
Theoretical guarantees for stochastic gradient sampling methods via Gaussian convolution inequalities
Daniel Paulin, Peter A. Whalley
We derive first-order (in the stepsize) bounds on the bias in Wasserstein distances of the invariant measure of stochastic gradient kinetic Langevin dynamics with minimal assumptio…
Randomised Splitting Methods and Stochastic Gradient Descent
Luke Shaw, Peter A. Whalley
We explore an explicit link between stochastic gradient descent using common batching strategies and splitting methods for ordinary differential equations. From this perspective, w…
Random Reshuffling for Stochastic Gradient Langevin Dynamics
Luke Shaw, Peter A. Whalley
We examine the use of different randomisation policies for stochastic gradient algorithms used in sampling, based on first-order (or overdamped) Langevin dynamics, the most popular…