Stochastic Gradient Riemannian Langevin Dynamics on the Probability Simplex
نویسندگان
چکیده
In this paper we investigate the use of Langevin Monte Carlo methods on the probability simplex and propose a new method, Stochastic gradient Riemannian Langevin dynamics, which is simple to implement and can be applied to large scale data. We apply this method to latent Dirichlet allocation in an online minibatch setting, and demonstrate that it achieves substantial performance improvements over the state of the art online variational Bayesian methods.
منابع مشابه
Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization
We present a unified framework to analyze the global convergence of Langevin dynamics based algorithms for nonconvex finite-sum optimization with n component functions. At the core of our analysis is a direct analysis of the ergodicity of the numerical approximations to Langevin dynamics, which leads to faster convergence rates. Specifically, we show that gradient Langevin dynamics (GLD) and st...
متن کاملApproximation Analysis of Stochastic Gradient Langevin Dynamics by using Fokker-Planck Equation and Ito Process
The stochastic gradient Langevin dynamics (SGLD) algorithm is appealing for large scale Bayesian learning. The SGLD algorithm seamlessly transit stochastic optimization and Bayesian posterior sampling. However, solid theories, such as convergence proof, have not been developed. We theoretically analyze the SGLD algorithm with constant stepsize in two ways. First, we show by using the Fokker-Pla...
متن کاملThe Effects of Different SDE Calculus on Dynamics of Nano-Aerosols Motion in Two Phase Flow Systems
Langevin equation for a nano-particle suspended in a laminar fluid flow was analytically studied. The Brownian motion generated from molecular bombardment was taken as a Wiener stochastic process and approximated by a Gaussian white noise. Euler-Maruyama method was used to solve the Langevin equation numerically. The accuracy of Brownian simulation was checked by performing a series of simulati...
متن کاملVariance Reduction in Stochastic Gradient Langevin Dynamics
Stochastic gradient-based Monte Carlo methods such as stochastic gradient Langevin dynamics are useful tools for posterior inference on large scale datasets in many machine learning applications. These methods scale to large datasets by using noisy gradients calculated using a mini-batch or subset of the dataset. However, the high variance inherent in these noisy gradients degrades performance ...
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 کامل