Hypocoercivity of piecewise deterministic Markov process-Monte Carlo

In this work, we establish $\mathrm{L}^2$-exponential convergence for a broad class of Piecewise Deterministic Markov Processes recently proposed in the context of Markov Process Monte Carlo methods and covering in particular the Randomized Hamiltonian Monte Carlo, the Zig-Zag process and the Bouncy Particle Sampler. The kernel of the symmetric part of the generator of such processes is non-trivial, and we follow the ideas recently introduced by (Dolbeault et al., 2009, 2015) to develop a rigorous framework for hypocoercivity in a fairly general and unifying set-up, while deriving tractable estimates of the constants involved in terms of the parameters of the dynamics. As a by-product we characterize the scaling properties of these algorithms with respect to the dimension of classes of problems, therefore providing some theoretical evidence to support their practical relevance.

[1]  C. Mouhot,et al.  Hypocoercivity for kinetic equations with linear relaxation terms , 2008, 0810.3493.

[2]  Daniel Han-Kwan,et al.  Geometric Analysis of the Linear Boltzmann Equation I. Trend to Equilibrium , 2014, 1401.8227.

[3]  J. M. Sanz-Serna,et al.  Randomized Hamiltonian Monte Carlo , 2015, 1511.09382.

[4]  S. Redon,et al.  Error Analysis of Modified Langevin Dynamics , 2016, 1601.07411.

[5]  M. Ledoux,et al.  Analysis and Geometry of Markov Diffusion Operators , 2013 .

[6]  Alain Durmus,et al.  Forward Event-Chain Monte Carlo: Fast Sampling by Randomness Control in Irreversible Markov Chains , 2017, Journal of Computational and Graphical Statistics.

[7]  S. Meyn,et al.  Geometric ergodicity and the spectral gap of non-reversible Markov chains , 2009, 0906.5322.

[8]  A. Doucet,et al.  Exponential ergodicity of the bouncy particle sampler , 2017, The Annals of Statistics.

[9]  Pierre Monmarch'e,et al.  A note on Fisher information hypocoercive decay for the linear Boltzmann equation , 2017, Analysis and Mathematical Physics.

[10]  P. Fearnhead,et al.  The Zig-Zag process and super-efficient sampling for Bayesian analysis of big data , 2016, The Annals of Statistics.

[11]  A. Faggionato,et al.  Non-equilibrium Thermodynamics of Piecewise Deterministic Markov Processes , 2009 .

[12]  D. Bakry,et al.  A simple proof of the Poincaré inequality for a large class of probability measures , 2008 .

[13]  Martin Grothaus,et al.  Hilbert space hypocoercivity for the Langevin dynamics revisited , 2016, 1608.07889.

[14]  Frédéric Hérau,et al.  Hypocoercivity and exponential time decay for the linear inhomogeneous relaxation Boltzmann equation , 2005, Asymptot. Anal..

[15]  S. G. Bobkov,et al.  Spectral Gap and Concentration for Some Spherically Symmetric Probability Measures , 2003 .

[16]  F. Hérau,et al.  Isotropic Hypoellipticity and Trend to Equilibrium for the Fokker-Planck Equation with a High-Degree Potential , 2004 .

[17]  Cl'ement Mouhot,et al.  Quantitative perturbative study of convergence to equilibrium for collisional kinetic models in the torus , 2006 .

[18]  Franca Hoffmann,et al.  Exponential Decay to Equilibrium for a Fiber Lay-Down Process on a Moving Conveyor Belt , 2016, SIAM J. Math. Anal..

[19]  Christian Schmeiser,et al.  Hypocoercivity without confinement , 2017, Pure and Applied Analysis.

[20]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[21]  Jun S. Liu,et al.  Monte Carlo strategies in scientific computing , 2001 .

[22]  D. Stroock,et al.  Logarithmic Sobolev inequalities and stochastic Ising models , 1987 .

[23]  S. Sénécal,et al.  Forward Event-Chain Monte Carlo: a general rejection-free and irreversible Markov chain simulation method , 2017 .

[24]  D. Vere-Jones Markov Chains , 1972, Nature.

[25]  A. Kennedy,et al.  Hybrid Monte Carlo , 1988 .

[26]  Mark H. A. Davis Piecewise-deterministic Markov processes , 1993 .

[27]  A. Eberle,et al.  Coupling and convergence for Hamiltonian Monte Carlo , 2018, The Annals of Applied Probability.

[28]  A. Doucet,et al.  Piecewise-Deterministic Markov Chain Monte Carlo , 2017, 1707.05296.

[29]  Christian P. Robert,et al.  Generalized Bouncy Particle Sampler , 2017, 1706.04781.

[30]  Martin Grothaus,et al.  A Hypocoercivity Related Ergodicity Method for Singularly Distorted Non-Symmetric Diffusions , 2015 .

[31]  É. Moulines,et al.  The tamed unadjusted Langevin algorithm , 2017, Stochastic Processes and their Applications.

[32]  M.H.A. Davis,et al.  Markov Models & Optimization , 1993 .

[33]  A. Doucet,et al.  The Bouncy Particle Sampler: A Nonreversible Rejection-Free Markov Chain Monte Carlo Method , 2015, 1510.02451.

[34]  Martin Grothaus,et al.  WEAK POINCARÉ INEQUALITIES FOR CONVERGENCE RATE OF DEGENERATE DIFFUSION PROCESSES By , 2018 .

[35]  E A J F Peters,et al.  Rejection-free Monte Carlo sampling for general potentials. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[36]  Cédric Villani,et al.  Hypocoercive Diffusion Operators , 2006 .

[37]  G. Roberts,et al.  Ergodicity of the zigzag process , 2017, The Annals of Applied Probability.

[38]  Arne Persson,et al.  Bounds for the Discrete Part of the Spectrum of a Semi-Bounded Schrödinger Operator. , 1960 .

[39]  Alain Durmus,et al.  Piecewise deterministic Markov processes and their invariant measures , 2018, Annales de l'Institut Henri Poincaré, Probabilités et Statistiques.

[40]  Michel Bonnefont,et al.  Spectral gap for spherically symmetric log-concave probability measures, and beyond , 2014, 1406.4621.

[41]  L. Hörmander Hypoelliptic second order differential equations , 1967 .

[42]  C. Mouhot,et al.  HYPOCOERCIVITY FOR LINEAR KINETIC EQUATIONS CONSERVING MASS , 2010, 1005.1495.

[43]  E. Pardoux,et al.  On the Poisson Equation and Diffusion Approximation. I Dedicated to N. v. Krylov on His Sixtieth Birthday , 2001 .

[44]  Martin Grothaus,et al.  Hypocoercivity for Kolmogorov backward evolution equations and applications , 2012, 1207.5447.

[45]  Richard L. Tweedie,et al.  Markov Chains and Stochastic Stability , 1993, Communications and Control Engineering Series.

[46]  E. Davies,et al.  Spectral Theory and Differential Operators: Index , 1995 .

[47]  M. Manhart,et al.  Markov Processes , 2018, Introduction to Stochastic Processes and Simulation.

[48]  A. Doucet,et al.  Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates , 2018, The Annals of Applied Probability.

[49]  Ryan O'Donnell,et al.  Analysis of Boolean Functions , 2014, ArXiv.

[50]  Josephine Evans Hypocoercivity in Phi-Entropy for the Linear Relaxation Boltzmann Equation on the Torus , 2021, SIAM J. Math. Anal..

[51]  Anton Arnold,et al.  On linear hypocoercive BGK models , 2015, 1510.02290.

[52]  M. Hairer,et al.  Spectral Properties of Hypoelliptic Operators , 2002 .

[53]  Martin Grothaus,et al.  Hypocoercivity of Langevin-type dynamics on abstract smooth manifolds , 2020, Stochastic Processes and their Applications.

[54]  Gareth O. Roberts,et al.  High-dimensional scaling limits of piecewise deterministic sampling algorithms , 2018, The Annals of Applied Probability.

[55]  Christian P. Robert,et al.  Monte Carlo Statistical Methods , 2005, Springer Texts in Statistics.

[56]  Werner Krauth,et al.  Generalized event-chain Monte Carlo: constructing rejection-free global-balance algorithms from infinitesimal steps. , 2013, The Journal of chemical physics.

[57]  P. Bhatnagar,et al.  A Model for Collision Processes in Gases. I. Small Amplitude Processes in Charged and Neutral One-Component Systems , 1954 .

[58]  Alain Durmus,et al.  Geometric ergodicity of the Bouncy Particle Sampler , 2018, The Annals of Applied Probability.