Transport map unadjusted Langevin algorithms: learning and discretizing perturbed samplers

• URL: http://arxiv.org/abs/2302.07227v4
• Date: Wed, 23 Oct 2024 03:18:35 GMT
• Title: Transport map unadjusted Langevin algorithms: learning and discretizing perturbed samplers
• Authors: Benjamin J. Zhang, Youssef M. Marzouk, Konstantinos Spiliopoulos,
• Abstract summary: We study the use of transport maps that normalize a target distribution as a way to precondition and accelerate the convergence of Langevin dynamics. We also show that applying a transport map to an irreversibly-perturbed ULA results in a geometry-informed irreversible perturbation (GiIrr) of the original dynamics.
• Score: 1.993607565985189
• License:
• Abstract: Langevin dynamics are widely used in sampling high-dimensional, non-Gaussian distributions whose densities are known up to a normalizing constant. In particular, there is strong interest in unadjusted Langevin algorithms (ULA), which directly discretize Langevin dynamics to estimate expectations over the target distribution. We study the use of transport maps that approximately normalize a target distribution as a way to precondition and accelerate the convergence of Langevin dynamics. We show that in continuous time, when a transport map is applied to Langevin dynamics, the result is a Riemannian manifold Langevin dynamics (RMLD) with metric defined by the transport map. We also show that applying a transport map to an irreversibly-perturbed ULA results in a geometry-informed irreversible perturbation (GiIrr) of the original dynamics. These connections suggest more systematic ways of learning metrics and perturbations, and also yield alternative discretizations of the RMLD described by the map, which we study. Under appropriate conditions, these discretized processes can be endowed with non-asymptotic bounds describing convergence to the target distribution in 2-Wasserstein distance. Illustrative numerical results complement our theoretical claims.

Related papers

• Probing hydrodynamic crossovers with dissipation-assisted operator evolution [0.0]
  We chart the emergence of diffusion in a generic interacting lattice model for varying U(1) charge densities. Our results clarify the dominant contributions to hydrodynamic correlation functions of conserved densities, and serve as a guide for generalizations to low temperature transport.
  arXiv  Detail & Related papers  (2024-08-15T16:39:10Z)
• An Improved Analysis of Langevin Algorithms with Prior Diffusion for Non-Log-Concave Sampling [27.882407333690267]
  We show that modified Langevin algorithm with prior diffusion can converge dimension independently for strongly log-concave target distributions. We also prove that the modified Langevin algorithm can also obtain the dimension-independent convergence of KL divergence with different step size schedules.
  arXiv  Detail & Related papers  (2024-03-10T11:50:34Z)
• Fisher information dissipation for time inhomogeneous stochastic differential equations [7.076726009680242]
  We provide a Lyapunov convergence analysis for time-inhomogeneous variable coefficient differential equations. Three typical examples include overdamped, irreversible drift, and underdamped Langevin dynamics.
  arXiv  Detail & Related papers  (2024-02-01T21:49:50Z)
• Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems [78.96969465641024]
  We extend mean-field Langevin dynamics to minimax optimization over probability distributions for the first time with symmetric and provably convergent updates. We also study time and particle discretization regimes and prove a new uniform-in-time propagation of chaos result.
  arXiv  Detail & Related papers  (2023-12-02T13:01:29Z)
• Proximal Algorithms for Accelerated Langevin Dynamics [57.08271964961975]
  We develop a novel class of MCMC algorithms based on a stochastized Nesterov scheme. We show superior performance of the proposed method over typical Langevin samplers for different models in statistics and image processing.
  arXiv  Detail & Related papers  (2023-11-24T19:56:01Z)
• Adaptive Annealed Importance Sampling with Constant Rate Progress [68.8204255655161]
  Annealed Importance Sampling (AIS) synthesizes weighted samples from an intractable distribution. We propose the Constant Rate AIS algorithm and its efficient implementation for $alpha$-divergences.
  arXiv  Detail & Related papers  (2023-06-27T08:15:28Z)
• Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction [49.66486092259376]
  The mean-field Langevin dynamics (MFLD) is a nonlinear generalization of the Langevin dynamics that incorporates a distribution-dependent drift. Recent works have shown that MFLD globally minimizes an entropy-regularized convex functional in the space of measures. We provide a framework to prove a uniform-in-time propagation of chaos for MFLD that takes into account the errors due to finite-particle approximation, time-discretization, and gradient approximation.
  arXiv  Detail & Related papers  (2023-06-12T16:28:11Z)
• Manifold Interpolating Optimal-Transport Flows for Trajectory Inference [64.94020639760026]
  We present a method called Manifold Interpolating Optimal-Transport Flow (MIOFlow) MIOFlow learns, continuous population dynamics from static snapshot samples taken at sporadic timepoints. We evaluate our method on simulated data with bifurcations and merges, as well as scRNA-seq data from embryoid body differentiation, and acute myeloid leukemia treatment.
  arXiv  Detail & Related papers  (2022-06-29T22:19:03Z)
• Convex Analysis of the Mean Field Langevin Dynamics [49.66486092259375]
  convergence rate analysis of the mean field Langevin dynamics is presented. $p_q$ associated with the dynamics allows us to develop a convergence theory parallel to classical results in convex optimization.
  arXiv  Detail & Related papers  (2022-01-25T17:13:56Z)
• Wasserstein Control of Mirror Langevin Monte Carlo [2.7145834528620236]
  Discretized Langevin diffusions are efficient Monte Carlo methods for sampling from high dimensional target densities. We consider Langevin diffusions on a Hessian-type manifold and study a discretization that is closely related to the mirror-descent scheme.
  arXiv  Detail & Related papers  (2020-02-11T13:16:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.