A smoothing stochastic gradient method for composite optimization

DOI10.1080/10556788.2014.891592zbMath1306.90108arXiv1008.5204MaRDI QIDQ2926083

Qihang Lin, Xi Chen, Javier F. Peña

Publication date: 29 October 2014

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1008.5204

zbMATH Keywords

smoothing; first-order method; stochastic gradient

Mathematics Subject Classification ID

90C30: Nonlinear programming

90C15: Stochastic programming

Related Items

Unnamed Item, Riemannian smoothing gradient type algorithms for nonsmooth optimization problem on compact Riemannian submanifold embedded in Euclidean space

Cites Work

• Unnamed Item
• Smooth minimization of non-smooth functions
• Gradient methods for minimizing composite functions
• An optimal method for stochastic composite optimization
• Smoothing proximal gradient method for general structured sparse regression
• Primal-dual first-order methods with \({\mathcal {O}(1/\varepsilon)}\) iteration-complexity for cone programming
• A coordinate gradient descent method for nonsmooth separable minimization
• Applications of second-order cone programming
• Introductory lectures on convex optimization. A basic course.
• Trace Norm Regularization: Reformulations, Algorithms, and Multi-Task Learning
• The Group Lasso for Logistic Regression
• Robust Stochastic Approximation Approach to Stochastic Programming
• Sparsity and Smoothness Via the Fused Lasso
• Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
• Model Selection and Estimation in Regression with Grouped Variables
• Interior Gradient and Proximal Methods for Convex and Conic Optimization