Proximal average approximated incremental gradient descent for composite penalty regularized empirical risk minimization

DOI10.1007/S10994-016-5609-1MaRDI QIDQ2398094zbMATH OpenOpenAlexFDO

Authors Yiu-ming Cheung, Jian Lou

Publication date 15 August 2017

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-016-5609-1

zbMATH Keywords

empirical risk minimizationproximal averagecomposite regularizerincremental gradient descent

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic approximation (62L20) Methods of reduced gradient type (90C52)

Recommendations

• Accelerated dual-averaging primal–dual method for composite convex minimization
• Distributed block-diagonal approximation methods for regularized empirical risk minimization
• Adaptive linearized alternating direction method of multipliers for non-convex compositely regularized optimization problems
• Incremental proximal gradient scheme with penalization for constrained composite convex optimization problems
• An adaptive superfast inexact proximal augmented Lagrangian method for smooth nonconvex composite optimization problems

Cites work

• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• A proximal stochastic gradient method with progressive variance reduction
• Analysis of multi-stage convex relaxation for sparse regularization
• Distributed optimization and statistical learning via the alternating direction method of multipliers
• Dual averaging methods for regularized stochastic learning and online optimization
• Grouping pursuit through a regularization solution surface
• Incremental majorization-minimization optimization with application to large-scale machine learning
• Introductory lectures on convex optimization. A basic course.
• Large-scale machine learning with stochastic gradient descent
• Nearly unbiased variable selection under minimax concave penalty
• Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
• Semi-stochastic coordinate descent
• Stochastic dual coordinate ascent methods for regularized loss minimization
• The Proximal Average: Basic Theory

Cited in

(5)

• An Efficient Algorithm for Minimizing Multi Non-Smooth Component Functions
• Inexact stochastic subgradient projection method for stochastic equilibrium problems with nonmonotone bifunctions: application to expected risk minimization in machine learning
• Integral resolvent and proximal mixtures
• Selective linearization for multi-block statistical learning
• Fixed point quasiconvex subgradient method

Describes a project that uses

Uses Software

• Finito
• Saga

This page was built for publication: Proximal average approximated incremental gradient descent for composite penalty regularized empirical risk minimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2398094)