Linear convergence of accelerated conditional gradient algorithms in spaces of measures

DOI10.1051/cocv/2021042zbMath1483.65089arXiv1904.09218MaRDI QIDQ4999535

Konstantin Pieper, Daniel Walter

Publication date: 7 July 2021

Published in: ESAIM: Control, Optimisation and Calculus of Variations (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1904.09218

zbMATH Keywords

nonsmooth optimization; sparsity; generalized conditional gradient; vector-valued finite Radon measures

Mathematics Subject Classification ID

65K05: Numerical mathematical programming methods

90C25: Convex programming

49M05: Numerical methods based on necessary conditions

46E27: Spaces of measures

65J22: Numerical solution to inverse problems in abstract spaces

Related Items

A generalized conditional gradient method for dynamic inverse problems with optimal transport regularization, Asymptotic linear convergence of fully-corrective generalized conditional gradient methods, Nonconvex regularization for sparse neural networks, On the linear convergence rates of exchange and continuous methods for total variation minimization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• D-optimal designs via a cocktail algorithm
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• A measure space approach to optimal source placement
• Inverse point source location with the Helmholtz equation on a bounded domain
• Elliptic optimal control problems with \(L^1\)-control cost and applications for the placement of control devices
• Exact support recovery for sparse spikes deconvolution
• Conditional gradient algorithms with open loop step size rules
• Some algorithmic aspects of the theory of optimal designs
• An introduction to \(\Gamma\)-convergence
• Model-oriented design of experiments
• Frequency-sparse optimal quantum control
• A unifying Radon-Nikodym theorem for vector measures
• Design of experiments in nonlinear models. Asymptotic normality, optimality criteria and small-sample properties
• Spike controls for elliptic and parabolic PDEs
• Sparsity of solutions for variational inverse problems with finite-dimensional data
• A sparse control approach to optimal sensor placement in PDE-constrained parameter estimation problems
• Spike detection from inaccurate samplings
• Optimal Control of the Undamped Linear Wave Equation with Measure Valued Controls
• Directional Sparsity in Optimal Control of Partial Differential Equations
• On linear-quadratic elliptic control problems of semi-infinite type
• A duality-based approach to elliptic control problems in non-reflexive Banach spaces
• Semi-Infinite Programming: Theory, Methods, and Applications
• Approximation of Elliptic Control Problems in Measure Spaces with Sparse Solutions
• Optimum Designs in Regression Problems
• Optimal Measurement Methods for Distributed Parameter System Identification
• Second-Order Derivatives of Extremal-Value Functions and Optimality Conditions for Semi-Infinite Programs
• Convergence Rates for Conditional Gradient Sequences Generated by Implicit Step Length Rules
• Some iterative procedures for generating nonsingular optimal designs
• Rates of Convergence for Conditional Gradient Algorithms Near Singular and Nonsingular Extremals
• Semismooth Newton Methods for Operator Equations in Function Spaces
• The Primal-Dual Active Set Strategy as a Semismooth Newton Method
• A simple proof of Singer’s representation theorem
• An extension of the frank and Wolfe method of feasible directions
• On Choosing and Bounding Probability Metrics
• Inverse problems in spaces of measures
• The Length of the Primal-Dual Path in Moreau--Yosida-Based Path-Following Methods for State Constrained Optimal Control
• A Semismooth Newton Method with Multidimensional Filter Globalization for $l_1$-Optimization
• Numerical analysis of sparse initial data identification for parabolic problems
• Measure Valued Directional Sparsity for Parabolic Optimal Control Problems
• The sliding Frank–Wolfe algorithm and its application to super-resolution microscopy
• Sparse Inverse Problems over Measures: Equivalence of the Conditional Gradient and Exchange Methods
• Towards a Mathematical Theory of Super‐resolution
• Linear convergence of a modified Frank–Wolfe algorithm for computing minimum-volume enclosing ellipsoids
• A Tight Upper Bound on the Rate of Convergence of Frank-Wolfe Algorithm
• The Sequential Generation of $D$-Optimum Experimental Designs
• The Alternating Descent Conditional Gradient Method for Sparse Inverse Problems