On perturbed proximal gradient algorithms
From MaRDI portal
Abstract: We study a version of the proximal gradient algorithm for which the gradient is intractable and is approximated by Monte Carlo methods (and in particular Markov Chain Monte Carlo). We derive conditions on the step size and the Monte Carlo batch size under which convergence is guaranteed: both increasing batch size and constant batch size are considered. We also derive non-asymptotic bounds for an averaged version. Our results cover both the cases of biased and unbiased Monte Carlo approximation. To support our findings, we discuss the inference of a sparse generalized linear model with random effect and the problem of learning the edge structure and parameters of sparse undirected graphical models.
Recommendations
- Convergence of stochastic proximal gradient algorithm
- Common fixed points of an infinite family of nonexpansive mappings in uniformly convex metric spaces
- Stochastic proximal-gradient algorithms for penalized mixed models
- A proximal stochastic gradient method with progressive variance reduction
- Proximal algorithms in statistics and machine learning
Cited in
(55)- General convergence analysis of stochastic first-order methods for composite optimization
- On the proximal gradient algorithm with alternated inertia
- Convergence of contrastive divergence algorithm in exponential family
- Computation for latent variable model estimation: a unified stochastic proximal framework
- Interacting particle Langevin algorithm for maximum marginal likelihood estimation
- On the accept-reject mechanism for Metropolis-Hastings algorithms
- CV@R-penalised portfolio optimisation with biased stochastic mirror descent
- Almost sure convergence of stochastic composite objective mirror descent for non-convex non-smooth optimization
- Stochastic forward-backward splitting for monotone inclusions
- On variance reduction for stochastic smooth convex optimization with multiplicative noise
- Statistical inference of constrained stochastic optimization via sketched sequential quadratic programming
- Unified analysis of stochastic gradient methods for composite convex and smooth optimization
- Stochastic quasi-Fejér block-coordinate fixed point iterations with random sweeping. II: Mean-square and linear convergence
- Gradient flows and randomised thresholding: sparse inversion and classification
- Proximal Gradient Methods for Machine Learning and Imaging
- Strong convergence of over-relaxed multi-parameter proximal scaled gradient algorithm and superiorization
- Optimization methods for large-scale machine learning
- Nonasymptotic convergence of stochastic proximal point methods for constrained convex optimization
- A dual-based stochastic inexact algorithm for a class of stochastic nonsmooth convex composite problems
- Dynamical behavior of a stochastic forward-backward algorithm using random monotone operators
- Stochastic variable metric proximal gradient with variance reduction for non-convex composite optimization
- Differentially private regularized stochastic convex optimization with heavy-tailed data
- Sparse estimation in Ising model via penalized Monte Carlo methods
- A unified convergence analysis of stochastic Bregman proximal gradient and extragradient methods
- Change-point computation for large graphical models: a scalable algorithm for Gaussian graphical models with change-points
- The stochastic auxiliary problem principle in Banach spaces: measurability and convergence
- A random block-coordinate Douglas-Rachford splitting method with low computational complexity for binary logistic regression
- A SAEM algorithm for fused Lasso penalized nonlinear mixed effect models: application to group comparison in pharmacokinetics
- Ergodic convergence of a stochastic proximal point algorithm
- Sharper Bounds for Proximal Gradient Algorithms with Errors
- Convergence of stochastic proximal gradient algorithm
- Maximum likelihood estimation of regularization parameters in high-dimensional inverse problems: an empirical Bayesian approach. I: Methodology and experiments
- Maximum likelihood estimation of regularization parameters in high-dimensional inverse problems: an empirical Bayesian approach. II: Theoretical analysis
- Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
- Consistent online Gaussian process regression without the sample complexity bottleneck
- Sequential sample average majorization-minimization
- A new random reshuffling method for nonsmooth nonconvex finite-sum optimization
- Regularized Rényi divergence minimization through Bregman proximal gradient algorithms
- Score-aware policy-gradient and performance guarantees using local Lyapunov stability
- Convergence analysis of the stochastic reflected forward-backward splitting algorithm
- The stochastic proximal distance algorithm
- A fully stochastic primal-dual algorithm
- Fast selection of nonlinear mixed effect models using penalized likelihood
- Convergence analysis of a proximal stochastic denoising regularization algorithm
- A strong law of large numbers for random monotone operators
- When Composite Likelihood meets Stochastic Approximation
- Minibatch forward-backward-forward methods for solving stochastic variational inequalities
- Stochastic proximal-gradient algorithms for penalized mixed models
- Statistical finite elements via interacting particle Langevin dynamics
- Stability of over-relaxations for the forward-backward algorithm, application to FISTA
- Exploiting multi-core architectures for reduced-variance estimation with intractable likelihoods
- scientific article; zbMATH DE number 7079312 (Why is no real title available?)
- High-performance statistical computing in the computing environments of the 2020s
- Perturbed iterate SGD for Lipschitz continuous loss functions
- SABRINA: a stochastic subspace majorization-minimization algorithm
This page was built for publication: On perturbed proximal gradient algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5361273)
