Classical Langevin dynamics for model Hamiltonians
نویسندگان
چکیده
منابع مشابه
Langevin dynamics of the Lebowitz–Percus model
We revisit the hard-spheres lattice gas model in the spherical approximation proposed by Lebowitz and Percus. Although no disorder is present in the model, we find that the short-range dynamical restrictions in the model induce glassy behaviour. We examine the offequilibrium Langevin dynamics of this model and study the relaxation of the density as well as the correlation, response and overlap ...
متن کاملConsistency and fluctuations for stochastic gradient Langevin dynamics Consistency and fluctuations for stochastic gradient Langevin dynamics
Applying standard Markov chain Monte Carlo (MCMC) algorithms to large data sets is computationally expensive. Both the calculation of the acceptance probability and the creation of informed proposals usually require an iteration through the whole data set. The recently proposed stochastic gradient Langevin dynamics (SGLD) method circumvents this problem by generating proposals which are only ba...
متن کاملDynamics of Langevin Simulations
This chapter reviews numerical simulations of quantum field theories based on stochastic quantization and the Langevin equation. The topics discussed include renormalization of finite stepsize algorithms, Fourier acceleration, and the relation of the Langevin equation to hybrid stochastic algorithms and hybrid Monte Carlo. Invited chapter to appear in the special supplement “Stochastic Quantiza...
متن کاملMirrored Langevin Dynamics
We generalize the Langevin Dynamics through the mirror descent framework for first-order sampling. The näıve approach of incorporating Brownian motion into the mirror descent dynamics, which we refer to as Symmetric Mirrored Langevin Dynamics (S-MLD), is shown to connected to the theory of Weighted Hessian Manifolds. The S-MLD, unfortunately, contains the hard instance of Cox–Ingersoll–Ross pro...
متن کاملNatural Langevin Dynamics for Neural Networks
One way to avoid overfitting in machine learning is to use model parameters distributed according to a Bayesian posterior given the data, rather than the maximum likelihood estimator. Stochastic gradient Langevin dynamics (SGLD) is one algorithm to approximate such Bayesian posteriors for large models and datasets. SGLD is a standard stochastic gradient descent to which is added a controlled am...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: physica status solidi (b)
سال: 2003
ISSN: 0370-1972,1521-3951
DOI: 10.1002/pssb.200301769