Sampling from non-smooth distributions through Langevin diffusion
From MaRDI portal
Publication:2065460
DOI10.1007/s11009-020-09809-7zbMath1477.60009OpenAlexW2615566168MaRDI QIDQ2065460
Christophe Chesneau, Tung Duy Luu, Jalal Fadili
Publication date: 7 January 2022
Published in: Methodology and Computing in Applied Probability (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s11009-020-09809-7
Monte CarloLangevin diffusionexponentially weighted aggregationnon-smooth distributionsproximal splitting
Monte Carlo methods (65C05) Computational methods for problems pertaining to probability theory (60-08)
Related Items (4)
On sampling from a log-concave density using kinetic Langevin diffusions ⋮ Smoothing unadjusted Langevin algorithms for nonsmooth composite potential functions ⋮ The forward-backward envelope for sampling with the overdamped Langevin algorithm ⋮ User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Bagging predictors
- Nonlinear total variation based noise removal algorithms
- Sparse regression learning by aggregation and Langevin Monte-Carlo
- Statistics for high-dimensional data. Methods, theory and applications.
- On the layered nearest neighbour estimate, the bagged nearest neighbour estimate and the random forest method in regression and classification
- Consistent group selection in high-dimensional linear regression
- Why the theorem of Scheffé should be rather called a theorem of Riesz
- Linear and convex aggregation of density estimators
- Some theoretical results on the grouped variables Lasso
- Near-ideal model selection by \(\ell _{1}\) minimization
- Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity
- The weighted majority algorithm
- Exponential convergence of Langevin distributions and their discrete approximations
- Aggregating regression procedures to improve performance
- Prox-regular functions in Hilbert spaces
- Boosting a weak learning algorithm by majority
- PAC-Bayesian estimation and prediction in sparse additive models
- Simultaneous analysis of Lasso and Dantzig selector
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
- PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting
- Simultaneous adaptation to the margin and to complexity in classification
- Proximal Markov chain Monte Carlo algorithms
- Exact matrix completion via convex optimization
- Low Complexity Regularization of Linear Inverse Problems
- PhaseLift: Exact and Stable Signal Recovery from Magnitude Measurements via Convex Programming
- Compressed sensing recovery via nonconvex shrinkage penalties
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
- Atomic Decomposition by Basis Pursuit
- Variational Analysis
- Bregman Monotone Optimization Algorithms
- Regularization of Wavelet Approximations
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
- A new approach to variable selection in least squares problems
- Local differentiability of distance functions
- Model selection with low complexity priors
- A Hamiltonian Monte Carlo Method for Non-Smooth Energy Sampling
- Sparsity and Smoothness Via the Fused Lasso
- Strong Convergence of Euler-Type Methods for Nonlinear Stochastic Differential Equations
- Prox-regular functions in variational analysis
- Uncertainty Principles and Vector Quantization
- Total Variation Projection With First Order Schemes
- Weakly decomposable regularization penalties and structured sparsity
- Aggregation by Exponential Weighting and Sharp Oracle Inequalities
- Model Selection and Estimation in Regression with Grouped Variables
- For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution
- A Useful Convergence Theorem for Probability Distributions
- Convex analysis and monotone operator theory in Hilbert spaces
- Random forests
- A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers
This page was built for publication: Sampling from non-smooth distributions through Langevin diffusion
