Consistency and fluctuations for stochastic gradient Langevin dynamics
From MaRDI portal
Publication:2810765
zbMATH Open1360.60144arXiv1409.0578MaRDI QIDQ2810765FDOQ2810765
Authors: Yee Whye Teh, Alexandre Thiery, Sebastian J. Vollmer 
Publication date: 6 June 2016
Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1409.0578
Recommendations
- Exploration of the (non-)asymptotic bias and variance of stochastic gradient Langevin dynamics
- On the stability of the stochastic gradient Langevin algorithm with dependent data stream
- Control variates for stochastic gradient MCMC
- scientific article; zbMATH DE number 6860839
- Laplacian smoothing stochastic gradient Markov chain Monte Carlo
Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Applications of Brownian motions and diffusion theory (population genetics, absorption problems, etc.) (60J70) Stochastic approximation (62L20)
Cited In (46)
- A langevinized ensemble Kalman filter for large-scale dynamic learning
- A probability approximation framework: Markov process approach
- Divide-and-conquer Metropolis-Hastings samplers with matched samples
- Weak approximation of transformed stochastic gradient MCMC
- Stochastic gradient MCMC for state space models
- Global convergence of stochastic gradient Hamiltonian Monte Carlo for nonconvex stochastic optimization: nonasymptotic performance bounds and momentum-based acceleration
- Exploration of the (non-)asymptotic bias and variance of stochastic gradient Langevin dynamics
- Central limit theorem and self-normalized Cramér-type moderate deviation for Euler-Maruyama scheme
- Coarse-gradient Langevin algorithms for dynamic data integration and uncertainty quantification
- Improving sampling accuracy of stochastic gradient MCMC methods via non-uniform subsampling of gradients
- Measuring sample quality with diffusions
- Merging MCMC subposteriors through Gaussian-process approximations
- Hamiltonian Monte Carlo with energy conserving subsampling
- Variance reduction for dependent sequences with applications to stochastic gradient MCMC
- A Stochastic Approximation-Langevinized Ensemble Kalman Filter Algorithm for State Space Models with Unknown Parameters
- Multi-variance replica exchange SGMCMC for inverse and forward problems via Bayesian PINN
- Multi-index antithetic stochastic gradient algorithm
- Bayesian computation: a summary of the current state, and samples backwards and forwards
- Mini-Batch Metropolis–Hastings With Reversible SGLD Proposal
- Perturbation theory for Markov chains via Wasserstein distance
- On stationary-point hitting time and ergodicity of stochastic gradient Langevin dynamics
- On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
- Stochastic gradient Markov chain Monte Carlo
- Adaptive thermostats for noisy gradient systems
- Functional central limit theorem and strong law of large numbers for stochastic gradient Langevin dynamics
- Bayesian Inference in Common Microeconometric Models With Massive Datasets by Double Marginalized Subsampling
- User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
- Multi-level Monte Carlo methods for the approximation of invariant measures of stochastic differential equations
- Stochastic gradient Langevin dynamics with adaptive drifts
- Nonasymptotic bounds for sampling algorithms without log-concavity
- Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
- Control variates for stochastic gradient MCMC
- Natural Langevin dynamics for neural networks
- Transport map accelerated adaptive importance sampling, and application to inverse problems arising from multiscale stochastic reaction networks
- On the stability of the stochastic gradient Langevin algorithm with dependent data stream
- Markov chains in random environment with applications in queuing theory and machine learning
- An adaptively weighted stochastic gradient MCMC algorithm for Monte Carlo simulation and global optimization
- The Bouncy Particle Sampler: A Non-Reversible Rejection-Free Markov Chain Monte Carlo Method
- Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics
- Weighted \(L^2\)-contractivity of Langevin dynamics with singular potentials
- Deep Compositional Spatial Models
- Laplacian smoothing stochastic gradient Markov chain Monte Carlo
- A probabilistic approach to tomography and adjoint state methods, with an application to full waveform inversion in medical ultrasound
- Title not available (Why is that?)
- Title not available (Why is that?)
- Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo
This page was built for publication: Consistency and fluctuations for stochastic gradient Langevin dynamics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2810765)
