A gradient-based bilevel optimization approach for tuning regularization hyperparameters

DOI10.1007/S11590-023-02057-XMaRDI QIDQ6968937zbMATH OpenFDO

Authors Ankur Sinha, Raja Mohanty

Publication date 23 June 2025

Published in Optimization Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S11590-023-02057-X

zbMATH Keywords

machine learningbilevel optimizationaugmented Lagrangian methodhyperparameter tuningmodel regularization

Mathematics Subject Classification ID

Game theory (91Axx) Mathematical programming (90Cxx) Numerical methods for mathematical programming, optimization and variational techniques (65Kxx)

Cites work

• scientific article; zbMATH DE number 4191395 (Why is no real title available?)
• scientific article; zbMATH DE number 6276119 (Why is no real title available?)
• A Branch and Bound Algorithm for the Bilevel Programming Problem
• A Representation and Economic Interpretation of a Two-Level Programming Problem
• A genetic algorithm using a finite search space for solving nonlinear/linear fractional bilevel programming problems
• A global optimization approach for the linear two-level program
• A penalty function approach for solving bi-level linear programs
• A solution method for the static constrained Stackelberg problem via penalty method
• A trust region algorithm for bilevel programming problems
• A trust region algorithm for nonlinear bilevel programming
• A trust-region method for nonlinear bilevel programming: algorithm and computational exper\-ience
• Bilevel linear programming
• Decision rule bounds for two-stage stochastic bilevel programs
• Descent approaches for quadratic bilevel programming
• Design and analysis of computer experiments. With comments and a rejoinder by the authors
• Double penalty method for bilevel optimization problems
• Efficient global optimization of expensive black-box functions
• Evolutionary algorithm for bilevel optimization using approximations of the lower level optimal solution mapping
• Finding optimal strategies in a multi-period multi-leader-follower Stackelberg game using an evolutionary algorithm
• Foundations of bilevel programming
• Genetic algorithm based approach to bi-level linear programming
• Global optimization of concave functions subject to quadratic constraints: An application in nonlinear bilevel programming
• Hyperband: a novel bandit-based approach to hyperparameter optimization
• Linear bilevel programming solution by genetic algorithm
• Mathematical Programs with Optimization Problems in the Constraints
• Necessary optimality conditions in pessimistic bilevel programming
• New necessary optimality conditions in optimistic bilevel programming
• Pessimistic bilevel optimization
• The steepest descent direction for the nonlinear bilevel programming problem

Cited in

(2)

• Derivative-free stochastic bilevel optimization for inverse problems
• A linear programming-based hyper local search for tuning hyperparameters

This page was built for publication: A gradient-based bilevel optimization approach for tuning regularization hyperparameters

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6968937)