15 citations · 53 across the 10 of their papers we have counts for
10 papers
Wasserstein Contraction of Coordinate Ascent Variational Inference
Rocco Caprio, Adrien Corenflos, Sam Power
We study the non-asymptotic contraction in Wasserstein distance of the sequential, parallel, and random-scan coordinate ascent variational inference algorithms. This is shown to ho…
Weak Poincaré Inequalities for Markov chains: theory and applications
Christophe Andrieu, Anthony Lee, Sam Power +1
We investigate the application of Weak Poincaré Inequalities (WPI) to Markov chains to study their rates of convergence and to derive complexity bounds. At a theoretical level we i…
A State-Space Perspective on Modelling and Inference for Online Skill Rating
Samuel Duffield, Samuel Power, Lorenzo Rimella
We summarise popular methods used for skill rating in competitive sports, along with their inferential paradigms and introduce new approaches based on sequential Monte Carlo and di…
Explicit convergence bounds for Metropolis Markov chains: isoperimetry, spectral gaps and profiles
Christophe Andrieu, Anthony Lee, Sam Power +1
We derive the first explicit bounds for the spectral gap of a random walk Metropolis algorithm on for any value of the proposal variance, which when scaled appropriately reco…
Adaptive Tuning for Metropolis Adjusted Langevin Trajectories
Lionel Riou-Durand, Pavel Sountsov, Jure Vogrinc +2
Hamiltonian Monte Carlo (HMC) is a widely used sampler for continuous probability distributions. In many cases, the underlying Hamiltonian dynamics exhibit a phenomenon of resonanc…
Poincaré inequalities for Markov chains: a meeting with Cheeger, Lyapunov and Metropolis
Christophe Andrieu, Anthony Lee, Sam Power +1
We develop a theory of weak Poincaré inequalities to characterize convergence rates of ergodic Markov chains. Motivated by the application of Markov chains in the context of algori…