Techniques for gradient-based bilevel optimization with non-smooth lower level problems
From MaRDI portal
Abstract: We propose techniques for approximating bilevel optimization problems with non-smooth lower level problems that can have a non-unique solution. To this end, we substitute the expression of a minimizer of the lower level minimization problem with an iterative algorithm that is guaranteed to converge to a minimizer of the problem. Using suitable non-linear proximal distance functions, the update mappings of such an iterative algorithm can be differentiable, notwithstanding the fact that the minimization problem is non-smooth.
Recommendations
- Bilevel optimization with nonsmooth lower level problems
- A primal nonsmooth reformulation for bilevel optimization problems
- Methodology and first-order algorithms for solving nonsmooth and non-strongly convex bilevel optimization problems
- On solving simple bilevel programs with a nonconvex lower level program
- scientific article; zbMATH DE number 1322063
Cites work
- scientific article; zbMATH DE number 410743 (Why is no real title available?)
- scientific article; zbMATH DE number 3296905 (Why is no real title available?)
- A bilevel optimization approach for parameter learning in variational models
- A first-order primal-dual algorithm for convex problems with applications to imaging
- Annotated Bibliography on Bilevel Programming and Mathematical Programs with Equilibrium Constraints
- Bilevel programming problems. Theory, algorithms and applications to energy networks
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Convex Analysis
- Descent Property and Global Convergence of the Fletcher—Reeves Method with Inexact Line Search
- Dynamic sampling schemes for optimal noise learning under multiple nonsmooth constraints
- Ergodic convergence to a zero of the sum of monotone operators in Hilbert space
- Evaluating Derivatives
- Function minimization by conjugate gradients
- Heavy-ball method in nonconvex optimization problems
- Image denoising: learning the noise model via nonsmooth PDE-constrained optimization
- Insights Into Analysis Operator Learning: From Patch-Based Sparse Models to Higher Order MRFs
- Large margin methods for structured and interdependent output variables
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- On the ergodic convergence rates of a first-order primal-dual algorithm
- On the limited memory BFGS method for large scale optimization
- Splitting Algorithms for the Sum of Two Nonlinear Operators
- Stein Unbiased GrAdient estimator of the Risk (SUGAR) for Multiple Parameter Selection
- Techniques for gradient-based bilevel optimization with non-smooth lower level problems
- The generalized Mangasarian-Fromowitz constraint qualification and optimality conditions for bilevel programs
- The structure of optimal parameters for image restoration problems
- iPiano: inertial proximal algorithm for nonconvex optimization
Cited in
(23)- Methodology and first-order algorithms for solving nonsmooth and non-strongly convex bilevel optimization problems
- Levenberg-Marquardt method and partial exact penalty parameter selection in bilevel optimization
- A non-convex denoising model for impulse and Gaussian noise mixture removing using bi-level parameter identification
- Uncertainty-safe large scale support vector machines
- Gradient-based solution algorithms for a class of bilevel optimization and optimal control problems with a nonsmooth lower level
- scientific article; zbMATH DE number 7626760 (Why is no real title available?)
- A regularized convolutional neural network for semantic image segmentation
- Convex Bi-level Optimization Problems with Nonsmooth Outer Objective Function
- Bilevel optimization methods in imaging
- Modern regularization methods for inverse problems
- Bilevel Methods for Image Reconstruction
- Convergence of a piggyback-style method for the differentiation of solutions of standard saddle-point problems
- Bilevel optimization with nonsmooth lower level problems
- Optimality Conditions for Bilevel Imaging Learning Problems with Total Variation Regularization
- A non-convex non-smooth bi-level parameter learning for impulse and Gaussian noise mixture removing
- A note on a bilevel problem for parameter learning for inverse problems with the wave equation
- Deep convolutional neural networks with spatial regularization, volume and star-shape priors for image segmentation
- Bilevel hyperparameter optimization for support vector classification: theoretical analysis and a solution method
- Linearly convergent bilevel optimization with single-step inner methods
- Techniques for gradient-based bilevel optimization with non-smooth lower level problems
- An Improved Unconstrained Approach for Bilevel Optimization
- Bilevel optimization: theory, algorithms, applications and a bibliography
- A primal nonsmooth reformulation for bilevel optimization problems
This page was built for publication: Techniques for gradient-based bilevel optimization with non-smooth lower level problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q334266)
