Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
From MaRDI portal
Publication:2058738
DOI10.1007/s11222-020-09986-yzbMath1475.62026arXiv1906.12281OpenAlexW3109346590MaRDI QIDQ2058738
Valentin De Bortoli, Ana F. Vidal, Alain Durmus, Marcelo Pereyra
Publication date: 9 December 2021
Published in: Statistics and Computing (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1906.12281
stochastic approximationMarkov chain Monte Carlo methodsrecursive estimationunadjusted Langevin algorithmempirical Bayesian inferencemaximum marginal likelihood estimation
Related Items (4)
Cost free hyper-parameter selection/averaging for Bayesian inverse problems with vanilla and Rao-blackwellized SMC samplers ⋮ The Split Gibbs Sampler Revisited: Improvements to Its Algorithmic Structure and Augmented Target Distribution ⋮ Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation ⋮ Maximum Entropy Methods for Texture Synthesis: Theory and Practice
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Reflection couplings and contraction rates for diffusions
- Convergence of adaptive and interacting Markov chain Monte Carlo algorithms
- Handbook of computational statistics. Concepts and methods.
- On the ergodicity properties of some adaptive MCMC algorithms
- Problems and theorems in analysis. I. Series, integral calculus, theory of functions. Transl. from the German by Dorothee Aeppli
- Exponential convergence of Langevin distributions and their discrete approximations
- Convergence of the Monte Carlo expectation maximization for curved exponential families.
- Geometric ergodicity of Metropolis algorithms
- Convergence of a stochastic approximation version of the EM algorithm
- Markov chains for exploring posterior distributions. (With discussion)
- Bayesian and frequentist regression methods
- Irreducibility and geometric ergodicity of Hamiltonian Monte Carlo
- Is there an analog of Nesterov acceleration for gradient-based MCMC?
- Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
- On sampling from a log-concave density using kinetic Langevin diffusions
- Couplings and quantitative contraction rates for Langevin dynamics
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
- Quantitative contraction rates for Markov chains on general state spaces
- (Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics
- Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
- Robust Stochastic Approximation Approach to Stochastic Programming
- Stability of Markovian processes I: criteria for discrete-time Chains
- Empirical Bayes: Past, Present and Future
- Markov Chains
- Handbook of Convex Optimization Methods in Imaging Science
- Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods
- Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo: When Langevin Meets Moreau
- Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach Part I: Methodology and Experiments
- Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach. Part II: Theoretical Analysis
- On perturbed proximal gradient algorithms
- Bayesian Inference for Logistic Models Using Pólya–Gamma Latent Variables
- An introduction to continuous optimization for imaging
- Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
- A Stochastic Approximation Method
This page was built for publication: Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
