Smoothing unadjusted Langevin algorithms for nonsmooth composite potential functions
From MaRDI portal
Publication:6090288
DOI10.1016/j.amc.2023.128377OpenAlexW4387630440MaRDI QIDQ6090288
Panagiotis Patrinos, Adam Arany, Yves Moreau, Susan Ghaderi, Masoud Ahookhosh, Alexander Skupin
Publication date: 14 November 2023
Published in: Applied Mathematics and Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.amc.2023.128377
Parametric inference (62Fxx) Mathematical programming (90Cxx) Probabilistic methods, stochastic differential equations (65Cxx)
Cites Work
- Unnamed Item
- Smooth minimization of non-smooth functions
- Recursive computation of the invariant distribution of a diffusion
- Lectures on convex optimization
- Exponential convergence of Langevin distributions and their discrete approximations
- Bayesian computation and stochastic systems. With comments and reply.
- Envelope functions: unifications and further properties
- Sampling from non-smooth distributions through Langevin diffusion
- Proximal nested sampling for high-dimensional Bayesian model selection
- User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
- Optimal subgradient methods: computational properties for large-scale linear inverse problems
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- Forward-backward quasi-Newton methods for nonsmooth optimization problems
- Random gradient-free minimization of convex functions
- Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
- Proximal Markov chain Monte Carlo algorithms
- The Bayesian elastic net
- Proximal Splitting Methods in Signal Processing
- A Stochastic Newton MCMC Method for Large-Scale Statistical Inverse Problems with Application to Seismic Inversion
- Smoothing and First Order Methods: A Unified Framework
- Accelerating Proximal Markov Chain Monte Carlo by Using an Explicit Stabilized Method
- Splitting Algorithms for the Sum of Two Nonlinear Operators
- Forward-Backward Envelope for the Sum of Two Nonconvex Functions: Further Properties and Nonmonotone Linesearch Algorithms
- First-Order Methods in Optimization
- Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo: When Langevin Meets Moreau
- Adaptive Rejection Sampling for Gibbs Sampling
- 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
- Equation of State Calculations by Fast Computing Machines
- Signal Recovery by Proximal Forward-Backward Splitting
- Proximité et dualité dans un espace hilbertien
- Expansion of the global error for numerical schemes solving stochastic differential equations
- A Bregman Forward-Backward Linesearch Algorithm for Nonconvex Composite Optimization: Superlinear Convergence to Nonisolated Local Minima
- Convex analysis and monotone operator theory in Hilbert spaces
- The forward-backward envelope for sampling with the overdamped Langevin algorithm
This page was built for publication: Smoothing unadjusted Langevin algorithms for nonsmooth composite potential functions
