First-order Methods for the Impatient: Support Identification in Finite Time with Convergent Frank--Wolfe Variants
From MaRDI portal
Publication:5233104
DOI10.1137/18M1206953zbMath1461.65132OpenAlexW2972033766WikidataQ127290317 ScholiaQ127290317MaRDI QIDQ5233104
Francesco Rinaldi, Samuel Rota Bulò, Immanuel M. Bomze
Publication date: 16 September 2019
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1137/18m1206953
Numerical mathematical programming methods (65K05) Large-scale problems in mathematical programming (90C06) Nonlinear programming (90C30)
Related Items
Frank--Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning ⋮ Fast Cluster Detection in Networks by First Order Optimization ⋮ Active-Set Identification with Complexity Guarantees of an Almost Cyclic 2-Coordinate Descent Method with Armijo Line Search ⋮ An almost cyclic 2-coordinate descent method for singly linearly constrained problems ⋮ Active Set Complexity of the Away-Step Frank--Wolfe Algorithm ⋮ Frank-Wolfe and friends: a journey into projection-free first-order optimization methods ⋮ A unified convergence framework for nonmonotone inexact decomposition methods ⋮ Trust Your Data or Not—StQP Remains StQP: Community Detection via Robust Standard Quadratic Optimization ⋮ Two-stage stochastic standard quadratic optimization ⋮ Minimization over the \(\ell_1\)-ball using an active-set non-monotone projected gradient ⋮ Avoiding bad steps in Frank-Wolfe variants
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- An active-set algorithmic framework for non-convex optimization problems over the simplex
- The complexity of optimizing over a simplex, hypercube or sphere: a short survey
- Large-scale active-set box-constrained optimization method with spectral projected gradients
- An active set feasible method for large-scale minimization problems with bound constraints
- ``Active-set complexity of proximal gradient: how long does it take to find the sparsity pattern?
- A two-stage active-set algorithm for bound-constrained optimization
- First-order methods almost always avoid strict saddle points
- Accelerated Block-coordinate Relaxation for Regularized Optimization
- Identifiable Surfaces in Constrained Optimization
- A New Active Set Algorithm for Box Constrained Optimization
- On the Identification of Active Constraints II: The Nonconvex Case
- Some comments on Wolfe's ‘away step’
- On the Identification of Active Constraints
- On the Goldstein-Levitin-Polyak gradient projection method
- Finding the Point of a Polyhedron Closest to the Origin
- Projected Newton Methods for Optimization Problems with Simple Constraints
This page was built for publication: First-order Methods for the Impatient: Support Identification in Finite Time with Convergent Frank--Wolfe Variants