Frank--Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning

DOI10.1137/20M1387869MaRDI QIDQ5055686FDOQ5055686

Authors: Haoyue Wang, Haihao Lu, Rahul Mazumder 

Publication date: 9 December 2022

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2012.15361

Recommendations

• Frank-Wolfe style algorithms for large scale optimization
• Generalized self-concordant analysis of Frank-Wolfe algorithms
• Generalized stochastic Frank-Wolfe algorithm with stochastic ``substitute gradient for structured convex optimization
• On the Frank-Wolfe algorithm for non-compact constrained optimization problems
• A novel Frank-Wolfe algorithm. Analysis and applications to large-scale SVM training

zbMATH Keywords

nuclear normgeneralized Lassotrend filteringsemidefinite optimizationFrank-Wolfe\(L1\) sparsity

Mathematics Subject Classification ID

Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Semidefinite programming (90C22) Computational methods for problems pertaining to operations research and mathematical programming (90-08)

Cites Work

• CVXPY: a Python-embedded modeling language for convex optimization
• Spectral regularization algorithms for learning large incomplete matrices
• Nonlinear total variation based noise removal algorithms
• Adaptive piecewise polynomial estimation via trend filtering
• Conic optimization via operator splitting and homogeneous self-dual embedding
• Sparsity and Smoothness Via the Fused Lasso
• Title not available (Why is that?)
• The solution path of the generalized lasso
• Introductory lectures on convex optimization. A basic course.
• Title not available (Why is that?)
• Exact matrix completion via convex optimization
• Flexible low-rank statistical modeling with missing data and side information
• Convex Analysis
• $\ell_1$ Trend Filtering
• Conditional gradient algorithms with open loop step size rules
• Coresets, sparse greedy approximation, and the Frank-Wolfe algorithm
• Conditional gradient algorithms for norm-regularized smooth convex optimization
• Sparse Approximate Solutions to Semidefinite Programs
• Title not available (Why is that?)
• New analysis and results for the Frank-Wolfe method
• Optimization Problems with Perturbations: A Guided Tour
• Some comments on Wolfe's ‘away step’
• Title not available (Why is that?)
• A Linearly Convergent Variant of the Conditional Gradient Algorithm under Strong Convexity, with Applications to Online and Stochastic Optimization
• Linearly convergent away-step conditional gradient for non-strongly convex functions
• Conditional gradient sliding for convex optimization
• Projection-free accelerated method for convex optimization
• Frank--Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning
• On the von Neumann and Frank-Wolfe algorithms with away steps
• An extended Frank-Wolfe method with ``in-face directions, and its application to low-rank matrix completion
• Polytope conditioning and linear convergence of the Frank-Wolfe algorithm
• The condition number of a function relative to a set
• Enforcing group structure through the group fused lasso
• First-order and stochastic optimization methods for machine learning
• Active set complexity of the away-step Frank-Wolfe algorithm
• First-order Methods for the Impatient: Support Identification in Finite Time with Convergent Frank--Wolfe Variants
• Weighted Matrix Completion and Recovery With Prior Subspace Information

Cited In (9)

• Frank-Wolfe style algorithms for large scale optimization
• Generalized stochastic Frank-Wolfe algorithm with stochastic ``substitute gradient for structured convex optimization
• A regularization of the Frank-Wolfe method and unification of certain nonlinear programming methods
• Frank--Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning
• Frank-Wolfe-type methods for a class of nonconvex inequality-constrained problems
• 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
• On the Frank-Wolfe algorithm for non-compact constrained optimization problems
• Generalized self-concordant analysis of Frank-Wolfe algorithms

Uses Software

• Mosek
• softImpute
• CVXPY
• SCS

This page was built for publication: Frank--Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5055686)