Accelerated Stochastic Gradient Method for Composite Regularization
Explore this paper's citation graph
Summary
On both general convex and strongly convex problems, the resultant approximation errors reduce at a faster rate than methods based on stochastic smoothing and ADMM, which is also veried experimentally on a number of synthetic and real-world data sets.
- Type
- article
- Published
- 2014-04-02
- Cited by
- 27
- References
- 26
- OpenAlex
- https://openalex.org/W78039530
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:18649457
Keywords
Smoothing, Regularization (linguistics), Proximal gradient methods for learning, Mathematical optimization, Minification
References
- The Proximal Average: Basic Theory
- The solution path of the generalized lasso
- The composite absolute penalties family for grouped and hierarchical variable selection
- Accelerated and Inexact Forward-Backward Algorithms
- An optimal method for stochastic composite optimization
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- Introductory Lectures on Convex Optimization - A Basic Course
- Regression Shrinkage and Selection via the Lasso
- Better Approximation and Faster Algorithm Using the Proximal Average
- Gradient methods for minimizing composite objective function
- Estimation of Simultaneously Sparse and Low Rank Matrices
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
- Accelerated Gradient Methods for Stochastic Optimization and Online Learning
- Smooth minimization of non-smooth functions
- Fast Newton-type Methods for Total Variation Regularization
- Stochastic Alternating Direction Method of Multipliers
- Proximal Splitting Methods in Signal Processing
- Dual Averaging Methods for Regularized Stochastic Learning and Online Optimization
- Stochastic Smoothing for Nonsmooth Minimizations: Accelerating SGD by Exploiting Structure
- Model Selection Through Sparse Maximum Likelihood Estimation for Multivariate Gaussian or Binary Data
Cited by
- A Survey of Stochastic Simulation and Optimization Methods in Signal Processing
- On the influence of momentum acceleration on online learning
- Proximal Average Approximated Incremental Gradient Method for Composite Penalty Regularized Empirical Risk Minimization
- Decoupled Asynchronous Proximal Stochastic Gradient Descent with Variance Reduction
- Proximal average approximated incremental gradient descent for composite penalty regularized empirical risk minimization
- Stochastic Three-Composite Convex Minimization
- Adaptive Proximal Average Approximation for Composite Convex Minimization
- Accelerated Variance Reduced Stochastic ADMM
- GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization
- Detection copy number variants profile by multiple constrained optimization
- A Solution Path Algorithm for General Parametric Quadratic Programming Problem
- Accelerated stochastic gradient method for support vector machines classification with additive kernel
- Stochastic Three-Composite Convex Minimization with a Linear Operator
- A Survey on the Low-Dimensional-Model-based Electromagnetic Imaging
- Adaptive Proximal Average Based Variance Reducing Stochastic Methods for Optimization with Composite Regularization
- Study on efficient sparse and low-rank optimization and its applications
- An Optimal Algorithm for Stochastic Three-Composite Optimization
- The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems
- Smoothed Variable Sample-Size Accelerated Proximal Methods for Nonsmooth Stochastic Convex Programs
- Randomized structure-adaptive optimization
Related papers
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- An optimal method for stochastic composite optimization
- Introductory Lectures on Convex Optimization: A Basic Course
- Accelerating Stochastic Gradient Descent using Predictive Variance Reduction
- Stochastic Alternating Direction Method of Multipliers
- A Stochastic Approximation Method
- Robust Stochastic Approximation Approach to Stochastic Programming
- Accelerated Gradient Methods for Stochastic Optimization and Online Learning
- Generalized non-convex non-smooth sparse and low rank minimization using proximal average