4 papers
Schedule optimization for tau-leaping in masked discrete diffusion
Cecilia Secchi, Giacomo Zanella
Masked diffusions are popular generative models for discrete distributions. Unlike standard autoregressive sampling, they reveal several coordinates in parallel, approximating each…
Hamiltonian dynamics for sampling on discrete spaces
Raphaël Barboni, Sebastiano Grazzi, Giacomo Zanella
We develop a general class of non-reversible Hamiltonian Monte Carlo dynamics on discrete state spaces. The method augments the discrete state with a continuous momentum variable a…
Spectral gap of Metropolis-within-Gibbs under log-concavity
Cecilia Secchi, Giacomo Zanella
The Metropolis-within-Gibbs (MwG) algorithm is a widely used Markov chain Monte Carlo method for sampling from high-dimensional distributions when exact conditional sampling is int…
Parallel computations for Metropolis Markov chains with Picard maps
Sebastiano Grazzi, Giacomo Zanella
We develop parallel algorithms for simulating zeroth-order (aka gradient-free) Metropolis Markov chains based on the Picard map. For Random Walk Metropolis Markov chains targeting…