Fluctuation without dissipation: Microcanonical Langevin Monte Carlo

• URL: http://arxiv.org/abs/2303.18221v2
• Date: Wed, 6 Dec 2023 15:34:52 GMT
• Title: Fluctuation without dissipation: Microcanonical Langevin Monte Carlo
• Authors: Jakob Robnik and Uro\v{s} Seljak
• Abstract summary: Langevin Monte Carlo sampling algorithms are inspired by physical systems in a heat bath. We show that the fluctuation-dissipation theorem is not required because only the configuration space distribution, and not the full phase space distribution, needs to be canonical. We propose a continuous-time Microcanonical Langevin Monte Carlo (MCLMC) as a dissipation-free system of differential equations (SDE)
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Stochastic sampling algorithms such as Langevin Monte Carlo are inspired by physical systems in a heat bath. Their equilibrium distribution is the canonical ensemble given by a prescribed target distribution, so they must balance fluctuation and dissipation as dictated by the fluctuation-dissipation theorem. In contrast to the common belief, we show that the fluctuation-dissipation theorem is not required because only the configuration space distribution, and not the full phase space distribution, needs to be canonical. We propose a continuous-time Microcanonical Langevin Monte Carlo (MCLMC) as a dissipation-free system of stochastic differential equations (SDE). We derive the corresponding Fokker-Planck equation and show that the stationary distribution is the microcanonical ensemble with the desired canonical distribution on configuration space. We prove that MCLMC is ergodic for any nonzero amount of stochasticity, and for smooth, convex potentials, the expectation values converge exponentially fast. Furthermore, the deterministic drift and the stochastic diffusion separately preserve the stationary distribution. This uncommon property is attractive for practical implementations as it implies that the drift-diffusion discretization schemes are bias-free, so the only source of bias is the discretization of the deterministic dynamics. We applied MCLMC on a lattice $\phi^4$ model, where Hamiltonian Monte Carlo (HMC) is currently the state-of-the-art integrator. For the same accuracy, MCLMC converges 12 times faster than HMC on an $8\times8$ lattice. On a $64\times64$ lattice, it is already 32 times faster. The trend is expected to persist to larger lattices, which are of particular interest, for example, in lattice quantum chromodynamics.

Related papers

• Macroscopic thermalization by unitary time-evolution in the weakly perturbed two-dimensional Ising model --- An application of the Roos-Teufel-Tumulka-Vogel theorem [0.0]
  We study thermalization in the two-dimensional Ising model in the low-temperature phase. It is proved that, for most choices of the random perturbation, the unitary time evolution $e-i(hatH_L+lambdahatV)t$ brings the initial state into thermal equilibrium.
  arXiv  Detail & Related papers  (2024-09-14T10:07:01Z)
• Closed-form solutions for the Salpeter equation [41.94295877935867]
  We study the propagator of the $1+1$ dimensional Salpeter Hamiltonian, describing a relativistic quantum particle with no spin. The analytical extension of the Hamiltonian in the complex plane allows us to formulate the equivalent problem, namely the B"aumer equation. This B"aumera corresponds to the Green function of a relativistic diffusion process that interpolates between Cauchy for small times and Gaussian diffusion for large times.
  arXiv  Detail & Related papers  (2024-06-26T15:52:39Z)
• Exact dynamics of quantum dissipative $XX$ models: Wannier-Stark localization in the fragmented operator space [49.1574468325115]
  We find an exceptional point at a critical dissipation strength that separates oscillating and non-oscillating decay. We also describe a different type of dissipation that leads to a single decay mode in the whole operator subspace.
  arXiv  Detail & Related papers  (2024-05-27T16:11:39Z)
• Entanglement Entropy Distributions of a Muon Decay [0.0]
  Divergences that occur in density matrices of decay and scattering processes are shown to be regularized by tracing and unitarity. These divergences are regularized by the lifetime of the decaying particle or the total scattering cross section. Also, this regularization is shown to give the expected helicities of final particles.
  arXiv  Detail & Related papers  (2023-12-10T00:02:34Z)
• 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)
• Machine learning in and out of equilibrium [58.88325379746631]
  Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels. We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium. We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
  arXiv  Detail & Related papers  (2023-06-06T09:12:49Z)
• Quantifying quantum chaos through microcanonical distributions of entanglement [0.0]
  A characteristic feature of "quantum chaotic" systems is that their eigenspectra and eigenstates display universal statistical properties described by random matrix theory (RMT) We introduce a quantitative metric for quantum chaos which utilizes the Kullback-Leibler divergence to compare the microcanonical distribution of entanglement entropy (EE) of midspectrum eigenstates with a reference RMT distribution generated by pure random states (with appropriate constraints) We study this metric in local minimally structured Floquet random circuits, as well as a canonical family of many-body Hamiltonians, the mixed field Ising model (MFIM
  arXiv  Detail & Related papers  (2023-05-19T18:00:05Z)
• Condition-number-independent Convergence Rate of Riemannian Hamiltonian Monte Carlo with Numerical Integrators [22.49731518828916]
  We show that for distributions in the form of $e-alphatopx$ on a polytope with $m constraints, the convergence rate of a family of commonly-used$$ is independent of $leftVert alpharightVert$ and the geometry of the polytope. These guarantees are based on a general bound on the convergence rate for densities of the form $e-f(x)$ in terms of parameters of the manifold and the integrator.
  arXiv  Detail & Related papers  (2022-10-13T17:46:51Z)
• Cycle Consistent Probability Divergences Across Different Spaces [38.43511529063335]
  Discrepancy measures between probability distributions are at the core of statistical inference and machine learning. This work proposes a novel unbalanced Monge optimal transport formulation for matching, up to isometries, distributions on different spaces.
  arXiv  Detail & Related papers  (2021-11-22T16:35:58Z)
• A Note on Optimizing Distributions using Kernel Mean Embeddings [94.96262888797257]
  Kernel mean embeddings represent probability measures by their infinite-dimensional mean embeddings in a reproducing kernel Hilbert space. We show that when the kernel is characteristic, distributions with a kernel sum-of-squares density are dense. We provide algorithms to optimize such distributions in the finite-sample setting.
  arXiv  Detail & Related papers  (2021-06-18T08:33:45Z)
• Spectral statistics in constrained many-body quantum chaotic systems [0.0]
  We study the spectral statistics of spatially-extended many-body quantum systems with on-site Abelian symmetries or local constraints. In particular, we analytically argue that in a system of length $L$ that conserves the $mth$ multipole moment, $t_mathrmTh$ scales subdiffusively as $L2(m+1)$.
  arXiv  Detail & Related papers  (2020-09-24T17:59:57Z)

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.