Birth-death dynamics for sampling: Global convergence, approximations and their asymptotics

• URL: http://arxiv.org/abs/2211.00450v3
• Date: Mon, 14 Aug 2023 21:57:23 GMT
• Title: Birth-death dynamics for sampling: Global convergence, approximations and their asymptotics
• Authors: Yulong Lu, Dejan Slep\v{c}ev, Lihan Wang
• Abstract summary: We build a practical numerical system based on the pure-death dynamics. We show that the kernelized dynamics converge on finite time intervals, to pure gradient-death dynamics shrinks to zero. Finally we prove the long-time results on the convergence of the states of the kernelized dynamics towards the Gibbs measure.
• Score: 9.011881058913184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Motivated by the challenge of sampling Gibbs measures with nonconvex potentials, we study a continuum birth-death dynamics. We improve results in previous works [51,57] and provide weaker hypotheses under which the probability density of the birth-death governed by Kullback-Leibler divergence or by $\chi^2$ divergence converge exponentially fast to the Gibbs equilibrium measure, with a universal rate that is independent of the potential barrier. To build a practical numerical sampler based on the pure birth-death dynamics, we consider an interacting particle system, which is inspired by the gradient flow structure and the classical Fokker-Planck equation and relies on kernel-based approximations of the measure. Using the technique of $\Gamma$-convergence of gradient flows, we show that on the torus, smooth and bounded positive solutions of the kernelized dynamics converge on finite time intervals, to the pure birth-death dynamics as the kernel bandwidth shrinks to zero. Moreover we provide quantitative estimates on the bias of minimizers of the energy corresponding to the kernelized dynamics. Finally we prove the long-time asymptotic results on the convergence of the asymptotic states of the kernelized dynamics towards the Gibbs measure.

Related papers

• Sampling with Adaptive Variance for Multimodal Distributions [14.121491356732188]
  We propose and analyze a class of distributions sampling algorithms for a bounded domain. We show that a derivative-free version can be used for sampling without information on the Gibbs potential.
  arXiv  Detail & Related papers  (2024-11-20T22:05:47Z)
• Quasi-Lindblad pseudomode theory for open quantum systems [6.184495862486372]
  We introduce a new framework to study the dynamics of open quantum systems with linearly coupled Gaussian baths. Our approach replaces the continuous bath with an auxiliary discrete set of pseudomodes with dissipative dynamics. We show that this quasi-Lindblad pseudomode formulation leads to a representation of the bath correlation function in terms of a complex weighted sum of complex exponentials.
  arXiv  Detail & Related papers  (2024-08-28T04:26:13Z)
• 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)
• Scaling of fronts and entanglement spreading during a domain wall melting [0.0]
  We revisit the out-of-equilibrium physics arising during the unitary evolution of a one-dimensional XXZ spin chain. In the last part of the work, we include large-scale quantum fluctuations on top of the semi-classical hydrodynamic background.
  arXiv  Detail & Related papers  (2023-03-17T15:34:43Z)
• Sampling with Mollified Interaction Energy Descent [57.00583139477843]
  We present a new optimization-based method for sampling called mollified interaction energy descent (MIED) MIED minimizes a new class of energies on probability measures called mollified interaction energies (MIEs) We show experimentally that for unconstrained sampling problems our algorithm performs on par with existing particle-based algorithms like SVGD.
  arXiv  Detail & Related papers  (2022-10-24T16:54:18Z)
• Slow semiclassical dynamics of a two-dimensional Hubbard model in disorder-free potentials [77.34726150561087]
  We show that introduction of harmonic and spin-dependent linear potentials sufficiently validates fTWA for longer times. In particular, we focus on a finite two-dimensional system and show that at intermediate linear potential strength, the addition of a harmonic potential and spin dependence of the tilt, results in subdiffusive dynamics.
  arXiv  Detail & Related papers  (2022-10-03T16:51:25Z)
• 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)
• Nonergodic dynamics of the one-dimensional Bose-Hubbard model with a trapping potential [0.0]
  We investigate nonergodic behavior of the one-dimensional Bose-Hubbard model. We compute the level spacing statistic, the time evolution of the number imbalance between the odd and the even sites, and the entanglement entropy.
  arXiv  Detail & Related papers  (2021-08-03T01:37:42Z)
• A Dynamical Central Limit Theorem for Shallow Neural Networks [48.66103132697071]
  We prove that the fluctuations around the mean limit remain bounded in mean square throughout training. If the mean-field dynamics converges to a measure that interpolates the training data, we prove that the deviation eventually vanishes in the CLT scaling.
  arXiv  Detail & Related papers  (2020-08-21T18:00:50Z)
• Probing eigenstate thermalization in quantum simulators via fluctuation-dissipation relations [77.34726150561087]
  The eigenstate thermalization hypothesis (ETH) offers a universal mechanism for the approach to equilibrium of closed quantum many-body systems. Here, we propose a theory-independent route to probe the full ETH in quantum simulators by observing the emergence of fluctuation-dissipation relations. Our work presents a theory-independent way to characterize thermalization in quantum simulators and paves the way to quantum simulate condensed matter pump-probe experiments.
  arXiv  Detail & Related papers  (2020-07-20T18:00:02Z)
• Steady-state Fano coherences in a V-type system driven by polarized incoherent light [0.0]
  We explore the properties of steady-state Fano coherences generated in a three-level V-system continuously pumped by polarized incoherent light. We attribute the surprising dephasing-induced enhancement of stationary Fano coherences to the environmental suppression of destructive interference of individual incoherent excitations.
  arXiv  Detail & Related papers  (2020-01-24T23:43:11Z)

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.