Papers

Published

A 4D-Var Method with Flow-Dependent Background Covariances for the Shallow-Water Equations

D. Paulin, A. Jasra, A. Beskos, D. Crisan - Statistics and Computing, 2022

Efficient MCMC Sampling with Dimension-Free Convergence Rate using ADMM-type Splitting

M. Vono, D. Paulin, A. Doucet - Journal of Machine Learning Research, 2021

Randomized Hamiltonian Monte Carlo as Scaling Limit of the Bouncy Particle Sampler and Dimension-Free Convergence Rates

G. Deligiannidis, D. Paulin, A. Doucet - Annals of Applied Probability, 2020

Dual Space Preconditioning for Gradient Descent

C.J. Maddison, D. Paulin, Y. W. Teh, A. Doucet - SIAM Journal on Optimization, 2020

Error Bounds for Sequential Monte Carlo Samplers for Multimodal Distributions

D. Paulin, A. Jasra, A. H. Thiery - Bernoulli, 2020

On Concentration Properties of Partially Observed Chaotic Systems

D. Paulin, A. Jasra, D. Crisan, A. Beskos - Advances in Applied Probability, 2018

Optimization Based Methods for Partially Observed Chaotic Systems

D. Paulin, A. Jasra, D. Crisan, A. Beskos - Foundations of Computational Mathematics, 2018

Mixing and Concentration by Ricci Curvature

D. Paulin - Journal of Functional Analysis, 2016.

Efron-Stein Inequalities for Random Matrices

D. Paulin, L. Mackey, J. A. Tropp - Annals of Probability, 2016

Hypothesis testing for Markov chain Monte Carlo

B. Gyori, D. Paulin - Statistics and Computing, 2016

Concentration inequalities for Markov chains by Marton couplings and spectral methods

D. Paulin - Electronic Journal of Probability, 2015

The convex distance inequality for dependent random variables, with applications to the stochastic travelling salesman and other problems

D. Paulin - Electronic Journal of Probability, 2014

Locally perturbed random walks with unbounded jumps

D. Paulin, D. Szász - Journal of Statistical Physics, 2010

Preprints

Hamiltonian Descent Methods

C.J. Maddison, D. Paulin, Y. W. Teh, B. O'Donoghue, A. Doucet

On Mixing Times of Metropolized Algorithm With Optimization Step (MAO) : A New Framework

E. M. Khribch, G. Deligiannidis, D. Paulin