Nonasymptotic bounds for sampling algorithms without log-concavity
From MaRDI portal
Publication:2657917
DOI10.1214/19-AAP1535zbMath1466.65008arXiv1808.07105OpenAlexW3021350626MaRDI QIDQ2657917
Lukasz Szpruch, Aleksandar Mijatović, Mateusz B. Majka
Publication date: 18 March 2021
Published in: The Annals of Applied Probability (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1808.07105
Computational methods in Markov chains (60J22) Estimation in multivariate analysis (62H12) Monte Carlo methods (65C05) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Numerical analysis or methods applied to Markov chains (65C40) Numerical solutions to stochastic differential and integral equations (65C30)
Related Items (16)
Central limit theorem and self-normalized Cramér-type moderate deviation for Euler-Maruyama scheme ⋮ Improved bounds for discretization of Langevin diffusions: near-optimal rates without convexity ⋮ Stochastic gradient Hamiltonian Monte Carlo for non-convex learning ⋮ Quantitative contraction rates for Markov chains on general state spaces ⋮ Strict Kantorovich contractions for Markov chains and Euler schemes with general noise ⋮ Distributed event-triggered unadjusted Langevin algorithm for Bayesian learning ⋮ Multi-index antithetic stochastic gradient algorithm ⋮ The forward-backward envelope for sampling with the overdamped Langevin algorithm ⋮ Unnamed Item ⋮ On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case ⋮ Approximation of heavy-tailed distributions via stable-driven SDEs ⋮ Multi-level Monte Carlo methods for the approximation of invariant measures of stochastic differential equations ⋮ Unadjusted Langevin algorithm for sampling a mixture of weakly smooth potentials ⋮ Maximum Entropy Methods for Texture Synthesis: Theory and Practice ⋮ Stochastic Gradient Markov Chain Monte Carlo ⋮ Convergence of a particle approximation for the quasi-stationary distribution of a diffusion process: Uniform estimates in a compact soft case
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Reflection couplings and contraction rates for diffusions
- Ergodic approximation of the distribution of a stationary diffusion: rate of convergence
- Curvature, concentration and error estimates for Markov chain Monte Carlo
- Reflection coupling and Wasserstein contractivity without convexity
- Recursive computation of the invariant distribution of a diffusion
- Fast Langevin based algorithm for MCMC in high dimensions
- Error analysis of randomized Runge-Kutta methods for differential equations with time-irregular coefficients
- Perturbation theory for Markov chains via Wasserstein distance
- Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
- Transportation cost for Gaussian and other product measures
- User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
- Measuring sample quality with diffusions
- Multi-level Monte Carlo methods for the approximation of invariant measures of stochastic differential equations
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- Control variates for stochastic gradient MCMC
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
- Recursive computation of the invariant measure of a stochastic differential equation driven by a Lévy process
- Strong approximation of solutions of stochastic differential equations with time-irregular coefficients via randomized Euler algorithm
- Langevin diffusions and the Metropolis-adjusted Langevin algorithm
- Statistical Romberg extrapolation: a new variance reduction method and applications to option pricing
- A random Euler scheme for Carathéodory differential equations
- Quantitative contraction rates for Markov chains on general state spaces
- Multilevel Monte Carlo method for ergodic SDEs without contractivity
- Exponential convergence in Lp-Wasserstein distance for diffusion processes without uniformly dissipative drift
- (Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics
- Multilevel Monte Carlo Methods
- Multilevel Monte Carlo Path Simulation
- Second-order discretization schemes of stochastic differential systems for the computation of the invariant law
- Exact solutions to the transportation problem on the line
- $V$-integrability, asymptotic stability and comparison property of explicit numerical schemes for non-linear SDEs
- Quantitative Harris-type theorems for diffusions and McKean–Vlasov processes
- Constructing Sampling Schemes via Coupling: Markov Semigroups and Optimal Transport
- Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
- Optimal Transport
This page was built for publication: Nonasymptotic bounds for sampling algorithms without log-concavity
