5 papers
Local Geometric Mixing via Dobrushin Contraction with Applications to Diffusion Path Monte Carlo and the Proximal Sampler
Stefan Oberdörster
Local geometric mixing localizes geometric mixing by requiring geometric convergence to equilibrium in total variation only over finitely many transitions. It accommodates local co…
On Accelerated Mixing of the No-U-turn Sampler
Stefan Oberdörster
Recent progress on the theory of variational hypocoercivity established that Randomized Hamiltonian Monte Carlo -- at criticality -- can achieve pronounced acceleration in its conv…
The No-Underrun Sampler: A Locally-Adaptive, Gradient-Free MCMC Method
Nawaf Bou-Rabee, Bob Carpenter, Sifan Liu +1
In this work, we introduce the No-Underrun Sampler (NURS), a locally-adaptive, gradient-free Markov chain Monte Carlo method that blends ideas from Hit-and-Run and the No-U-Turn Sa…
Ballistic Convergence in Hit-and-Run Monte Carlo and a Coordinate-free Randomized Kaczmarz Algorithm
Nawaf Bou-Rabee, Andreas Eberle, Stefan Oberdörster
Hit-and-Run is a coordinate-free Gibbs sampler, yet the quantitative advantages of its coordinate-free property remain largely unexplored beyond empirical studies. In this paper, w…
Mixing of the No-U-Turn Sampler and the Geometry of Gaussian Concentration
Nawaf Bou-Rabee, Stefan Oberdörster
We prove that the mixing time of the No-U-Turn Sampler (NUTS), when initialized in the concentration region of the canonical Gaussian measure, scales as , up to logarithmi…