Multi-index antithetic stochastic gradient algorithm

DOI10.1007/s11222-023-10220-8zbMath1516.62019arXiv2006.06102OpenAlexW3035730397MaRDI QIDQ6171790

Marc Sabate Vidales, Lukasz Szpruch, Mateusz B. Majka

Publication date: 18 July 2023

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.06102

zbMATH Keywords

Langevin dynamicsstochastic gradientmulti-level Monte Carloapproximate sampling

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Computational methods for problems pertaining to statistics (62-08) Monte Carlo methods (65C05)

Cites Work

• Unnamed Item
• Unnamed Item
• Multi-index Monte Carlo: when sparsity meets sampling
• Multi-level stochastic approximation algorithms
• Reflection couplings and contraction rates for diffusions
• Laplace's method revisited: Weak convergence of probability measures
• Fast Langevin based algorithm for MCMC in high dimensions
• General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
• General multilevel adaptations for stochastic approximation algorithms. II: CLTs
• Central limit theorem for the multilevel Monte Carlo Euler method
• 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
• Control variates for stochastic gradient MCMC
• Iterative multilevel particle approximation for McKean-Vlasov SDEs
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Langevin diffusions and the Metropolis-adjusted Langevin algorithm
• Statistical Romberg extrapolation: a new variance reduction method and applications to option pricing
• Antithetic multilevel Monte Carlo estimation for multi-dimensional SDEs without Lévy area simulation
• Non-asymptotic error bounds for the multilevel Monte Carlo Euler method applied to SDEs with constant diffusion coefficient
• Quantitative contraction rates for Markov chains on general state spaces
• Nonasymptotic bounds for sampling algorithms without log-concavity
• Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization
• Unbiased Estimation with Square Root Convergence for SDE Models
• (Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics
• Multilevel Monte Carlo Methods
• Antithetic Multilevel Monte Carlo Estimation for Multidimensional SDEs
• Multilevel Monte Carlo Path Simulation
• Quantitative Harris-type theorems for diffusions and McKean–Vlasov processes
• Unbiased multi-index Monte Carlo
• 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
• Unbiased Markov Chain Monte Carlo Methods with Couplings
• On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case
• Sampling can be faster than optimization
• Multilevel Nested Simulation for Efficient Risk Estimation
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Stochastic Gradient Markov Chain Monte Carlo
• Optimal Transport

This page was built for publication: Multi-index antithetic stochastic gradient algorithm