2 citations · 4 across the 3 of their papers we have counts for
4 papers
Dual Space Preconditioning for Gradient Descent
Chris J. Maddison, Daniel Paulin, Yee Whye Teh +1
The conditions of relative smoothness and relative strong convexity were recently introduced for the analysis of Bregman gradient methods for convex optimization. We introduce a ge…
Randomized Hamiltonian Monte Carlo as Scaling Limit of the Bouncy Particle Sampler and Dimension-Free Convergence Rates
George Deligiannidis, Daniel Paulin, Alexandre Bouchard-Côté +1
The Bouncy Particle Sampler is a Markov chain Monte Carlo method based on a nonreversible piecewise deterministic Markov process. In this scheme, a particle explores the state spac…
Concentration Inequalities in Locally Dependent Spaces
Daniel Paulin
This paper studies concentration inequalities for functions of locally dependent random variables. We show that the usual definition of local dependence does not imply concentratio…
A Note on Matrix Concentration Inequalities via the Method of Exchangeable Pairs
Daniel Paulin
The aim of this paper is to prove an improved version of the bounded differences inequality for matrix valued functions, by developing the methods of Mackey et al.: "Matrix Concent…