Frank-Wolfe and friends: a journey into projection-free first-order optimization methods
From MaRDI portal
Publication:2240671
Abstract: Invented some 65 years ago in a seminal paper by Marguerite Straus-Frank and Philip Wolfe, the Frank-Wolfe method recently enjoys a remarkable revival, fuelled by the need of fast and reliable first-order optimization methods in Data Science and other relevant application areas. This review tries to explain the success of this approach by illustrating versatility and applicability in a wide range of contexts, combined with an account on recent progress in variants, both improving on the speed and efficiency of this surprisingly simple principle of first-order optimization.
Recommendations
- On the Frank-Wolfe algorithm for non-compact constrained optimization problems
- Frank-Wolfe algorithm from optimization to equilibrium problems
- Extension of the Frank-Wolfe algorithm to concave nondifferentiable objective functions
- Riemannian optimization via Frank-Wolfe methods
- A regularization of the Frank-Wolfe method and unification of certain nonlinear programming methods
- Frank-Wolfe style algorithms for large scale optimization
- A modified Frank-Wolfe algorithm and its convergence properties
- Frank-Wolfe method for solving a class of nonlinear bilevel programming problems
- Revisiting the approximate Carathéodory problem via the Frank-Wolfe algorithm
- Short paper -- A note on the Frank-Wolfe algorithm for a class of nonconvex and nonsmooth optimization problems
Cites work
- scientific article; zbMATH DE number 6118217 (Why is no real title available?)
- scientific article; zbMATH DE number 3526459 (Why is no real title available?)
- scientific article; zbMATH DE number 1215260 (Why is no real title available?)
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 1391397 (Why is no real title available?)
- scientific article; zbMATH DE number 7064051 (Why is no real title available?)
- scientific article; zbMATH DE number 3293978 (Why is no real title available?)
- scientific article; zbMATH DE number 3345848 (Why is no real title available?)
- A Linearly Convergent Variant of the Conditional Gradient Algorithm under Strong Convexity, with Applications to Online and Stochastic Optimization
- A Tight Upper Bound on the Rate of Convergence of Frank-Wolfe Algorithm
- A framework for and empirical study of algorithms for traffic assignment
- A general regularized continuous formulation for the maximum clique problem
- A modified Frank--Wolfe algorithm for computing minimum-area enclosing ellipsoidal cylinders: theory and algorithms
- A review on algorithms for maximum clique problems
- Active set complexity of the away-step Frank-Wolfe algorithm
- An active-set algorithmic framework for non-convex optimization problems over the simplex
- An extended Frank-Wolfe method with ``in-face directions, and its application to low-rank matrix completion
- An extension of the frank and Wolfe method of feasible directions
- Approximate minimum enclosing balls in high dimensions using core-sets
- Atomic decomposition by basis pursuit
- Concave programming for minimizing the zero-norm over polyhedral sets
- Conditional gradient algorithms for norm-regularized smooth convex optimization
- Conditional gradient algorithms with open loop step size rules
- Conditional gradient sliding for convex optimization
- Convex optimization algorithms
- Coresets, sparse greedy approximation, and the Frank-Wolfe algorithm
- Evolution towards the maximum clique
- Exact matrix completion via convex optimization
- Finding the Point of a Polyhedron Closest to the Origin
- Finding the nearest point in A polytope
- First-order Methods for the Impatient: Support Identification in Finite Time with Convergent Frank--Wolfe Variants
- First-order and stochastic optimization methods for machine learning
- First-order methods of smooth convex optimization with inexact oracle
- Learning with submodular functions: a convex optimization perspective
- Lexicographically Optimal Base of a Polymatroid with Respect to a Weight Vector
- Linear convergence of a modified Frank–Wolfe algorithm for computing minimum-volume enclosing ellipsoids
- Linearly convergent away-step conditional gradient for non-strongly convex functions
- New analysis and results for the Frank-Wolfe method
- Polytope conditioning and linear convergence of the Frank-Wolfe algorithm
- Rates of Convergence for Conditional Gradient Algorithms Near Singular and Nonsingular Extremals
- Scalable robust matrix recovery: Frank-Wolfe meets proximal methods
- Simplicial decomposition in nonlinear programming algorithms
- Simplified versions of the conditional gradient method
- Solving standard quadratic optimization problems via linear, semidefinite and copositive pro\-gramming
- Some comments on Wolfe's ‘away step’
- The condition number of a function relative to a set
- The cyclic block conditional gradient method for convex optimization problems
- Two Algorithms for the Minimum Enclosing Ball Problem
Cited in
(8)- First-order Methods for the Impatient: Support Identification in Finite Time with Convergent Frank--Wolfe Variants
- 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
- 21 volumes for the 21st century
- Catching-up algorithm with approximate projections for Moreau's sweeping processes
- Avoiding bad steps in Frank-Wolfe variants
- Two-stage stochastic standard quadratic optimization
- The Frank-Wolfe algorithm: a short introduction
This page was built for publication: Frank-Wolfe and friends: a journey into projection-free first-order optimization methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2240671)
