Timezone: »

NEO: Non Equilibrium Sampling on the Orbits of a Deterministic Transform
Achille Thin · Yazid Janati El Idrissi · Sylvain Le Corff · Charles Ollion · Eric Moulines · Arnaud Doucet · Alain Durmus · Christian X Robert

Thu Dec 09 12:30 AM -- 02:00 AM (PST) @ Virtual #None
Sampling from a complex distribution $\pi$ and approximating its intractable normalizing constant $\mathrm{Z}$ are challenging problems. In this paper, a novel family of importance samplers (IS) and Markov chain Monte Carlo (MCMC) samplers is derived. Given an invertible map $\mathrm{T}$, these schemes combine (with weights) elements from the forward and backward Orbits through points sampled from a proposal distribution $\rho$. The map $\mathrm{T}$ does not leave the target $\pi$ invariant, hence the name NEO, standing for Non-Equilibrium Orbits. NEO-IS provides unbiased estimators of the normalizing constant and self-normalized IS estimators of expectations under $\pi$ while NEO-MCMC combines multiple NEO-IS estimates of the normalizing constant and an iterated sampling-importance resampling mechanism to sample from $\pi$. For $\mathrm{T}$ chosen as a discrete-time integrator of a conformal Hamiltonian system, NEO-IS achieves state-of-the art performance on difficult benchmarks and NEO-MCMC is able to explore highly multimodal targets. Additionally, we provide detailed theoretical results for both methods. In particular, we show that NEO-MCMC is uniformly geometrically ergodic and establish explicit mixing time estimates under mild conditions.

Author Information

Achille Thin (Ecole polytechnique)
Yazid Janati El Idrissi (telecom sudparis)
Sylvain Le Corff (Telecom SudParis)
Charles Ollion (Ecole polytechnique)
Eric Moulines (Ecole Polytechnique)
Arnaud Doucet (Google DeepMind)
Alain Durmus (ENS Paris Saclay)
Christian X Robert (Université Paris-Dauphine)

More from the Same Authors