Poster

Orbital MCMC

Kirill Neklyudov · Max Welling

Virtual
[ Abstract ]
Wed 30 Mar 8:30 a.m. PDT — 10 a.m. PDT
 
Oral presentation: Oral 8: Learning theory / Sampling methods
Wed 30 Mar midnight PDT — 1 a.m. PDT

Abstract:

Markov Chain Monte Carlo (MCMC) algorithms ubiquitously employ complex deterministic transformations to generate proposal points that are then filtered by the Metropolis-Hastings-Green (MHG) test. However, the condition of the target measure invariance puts restrictions on the design of these transformations. In this paper, we first derive the acceptance test for the stochastic Markov kernel considering arbitrary deterministic maps as proposal generators. When applied to the transformations with orbits of period two (involutions), the test reduces to the MHG test. Based on the derived test we propose two practical algorithms: one operates by constructing periodic orbits from any diffeomorphism, another on contractions of the state space (such as optimization trajectories). Finally, we perform an empirical study demonstrating the practical advantages of both kernels.

Chat is not available.