Variance Reduction for Dependent Sequences with Applications to Stochastic Gradient MCMC

DOI10.1137/19M1301199zbMath1478.60206arXiv2008.06858OpenAlexW3159529756MaRDI QIDQ4995114

Denis Belomestny, S. P. Samsonov, Leonid Iosipoi, Alexey Naumov, Eric Moulines

Publication date: 23 June 2021

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2008.06858

zbMATH Keywords

variance reductionMCMC algorithmsgenerative modelsstochastic gradient

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Numerical analysis or methods applied to Markov chains (65C40)

Related Items (1)

Empirical variance minimization with applications in variance reduction and optimal control

Uses Software

• Saga

Cites Work

• Zero variance Markov chain Monte Carlo for Bayesian estimators
• Exploiting multi-core architectures for reduced-variance estimation with intractable likelihoods
• On some non asymptotic bounds for the Euler scheme
• Informative \(g\)-priors for logistic regression
• Exponential integrability and transportation cost related to logarithmic Sobolev inequalities
• Exponential convergence of Langevin distributions and their discrete approximations
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• A new weak dependence condition and applications to moment inequalities
• Variance reduction in Monte Carlo estimators via empirical variance minimization
• Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
• Transportation cost for Gaussian and other product measures
• Variance reduction for Markov chains with application to MCMC
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Control variates for stochastic gradient MCMC
• Batch means and spectral variance estimators in Markov chain Monte Carlo
• Bounding \(\bar d\)-distance by informational divergence: A method to prove measure concentration
• Bracketing metric entropy rates and empirical central limit theorems for function classes of Besov- and Sobolev-type
• Simulation and the Monte Carlo Method
• Markov Chains
• Control Variates for Estimation Based on Reversible Markov Chain Monte Carlo Samplers
• Analysis and Geometry of Markov Diffusion Operators
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Control Functionals for Monte Carlo Integration
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Variance Reduction for Dependent Sequences with Applications to Stochastic Gradient MCMC