Frank-Wolfe style algorithms for large scale optimization

DOI10.1007/978-3-319-97478-1_9MaRDI QIDQ2415206zbMATH OpenOpenAlexFDO

Authors Lijun Ding, Madeleine Udell

Publication date 21 May 2019

Full work available at URL https://arxiv.org/abs/1808.05274

zbMATH Keywords

Frank-Wolfe algorithmlarge scale optimizationlow memory optimizationmatrix completionstochastic gradient

Mathematics Subject Classification ID

Large-scale problems in mathematical programming (90C06) Convex programming (90C25)

Abstract: We introduce a few variants on Frank-Wolfe style algorithms suitable for large scale optimization. We show how to modify the standard Frank-Wolfe algorithm using stochastic gradients, approximate subproblem solutions, and sketched decision variables in order to scale to enormous problems while preserving (up to constants) the optimal convergence rate $mathcalO(frac1k)$.

Recommendations

• Fast and scalable Lasso via stochastic Frank-Wolfe methods with a convergence guarantee
• A novel Frank-Wolfe algorithm. Analysis and applications to large-scale SVM training
• Generalized stochastic Frank-Wolfe algorithm with stochastic ``substitute gradient for structured convex optimization
• New analysis and results for the Frank-Wolfe method
• Frank--Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning

Cited in

(16)

• Generalized stochastic Frank-Wolfe algorithm with stochastic ``substitute gradient for structured convex optimization
• Restarting Frank-Wolfe: faster rates under Hölderian error bounds
• Frank-Wolfe and friends: a journey into projection-free first-order optimization methods
• Generalized self-concordant analysis of Frank-Wolfe algorithms
• Fast and scalable Lasso via stochastic Frank-Wolfe methods with a convergence guarantee
• Frank--Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning
• FrankWolfe.jl: A High-Performance and Flexible Toolbox for Frank–Wolfe Algorithms and Conditional Gradients
• A novel Frank-Wolfe algorithm. Analysis and applications to large-scale SVM training
• Frank-Wolfe algorithm from optimization to equilibrium problems
• New analysis and results for the Frank-Wolfe method
• Large-Scale Nonconvex Optimization: Randomization, Gap Estimation, and Numerical Resolution
• The Frank-Wolfe algorithm: a short introduction
• Inexact and stochastic generalized conditional gradient with augmented Lagrangian and proximal step
• Scalable Frank-Wolfe on generalized self-concordant functions via simple steps
• Using Taylor-approximated gradients to improve the Frank-Wolfe method for empirical risk minimization
• Catching-up algorithm with approximate projections for Moreau's sweeping processes

This page was built for publication: Frank-Wolfe style algorithms for large scale optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2415206)