12 papers
On couplings for kinetic Langevin diffusions
Nawaf Bou-Rabee, Sonja Cox, Roy Schieven
For the kinetic Langevin diffusion and its splitting discretizations, the hypoelliptic noise structure makes the relationship between couplings and total variation (TV) bounds more…
Neural Quantum States in Mixed Precision
Massimo Solinas, Agnes Valenti, Nawaf Bou-Rabee +1
Scientific computing has long relied on double precision (64-bit floating point) arithmetic to guarantee accuracy in simulations of real-world phenomena. However, the growing avail…
Tail-Sensitive KL and Rényi Convergence of Unadjusted Hamiltonian Monte Carlo via One-Shot Couplings
Nawaf Bou-Rabee, Siddharth Mitra, Andre Wibisono
Hamiltonian Monte Carlo (HMC) algorithms are among the most widely used sampling methods in high dimensional settings, yet their convergence properties are poorly understood in div…
From Continuous to Discrete: a No-U-Turn Sampler for Permutations
Nawaf Bou-Rabee, Zichu Wang
We introduce a discrete-space analogue of the No-U-Turn sampler on the symmetric group , yielding a locally adaptive and reversible Markov chain Monte Carlo method for $\mathr…
Decoupling for Markov Chains
Nawaf Bou-Rabee, Victor H. de la Peña
Consider a Markov chain with invariant measure that admits the representation , where are i.i.d. random variables and …
GIST: Gibbs self-tuning for locally adaptive Hamiltonian Monte Carlo
Nawaf Bou-Rabee, Bob Carpenter, Milo Marsden
We introduce a novel and flexible framework for constructing locally adaptive Hamiltonian Monte Carlo (HMC) samplers by Gibbs sampling the algorithm's tuning parameters conditional…