Karush-Kuhn-Tucker conditions and Lagrangian approach for improving machine learning techniques: a survey and new developments

Publication date: 3 December 2024

Published in: Atti della Accademia Peloritana dei Pericolanti. Classe di Scienze Fisiche, Matemàtiche e Naturali (Search for Journal in Brave)

zbMATH Keywords

nonlinear programming support vector machines margin classifier KKT conditions and Lagrangian

Mathematics Subject Classification ID

Convex programming (90C25) Nonlinear programming (90C30) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Enhanced Karush-Kuhn-Tucker condition and weaker constraint qualifications
New order relations in set optimization
On approximate KKT condition and its extension to continuous variational inequalities
Approximate Karush-Kuhn-Tucker condition in multiobjective optimization
Modified Kuhn-Tucker conditions when a minimum is not attained
Discrete support vector decision trees via tabu search
The algebra of many-valued quantities
On generalized derivatives for \(C^{1,1}\) vector optimization problems
Support-vector networks
Extended Karush-Kuhn-Tucker condition for constrained interval optimization problems and its application in support vector machines
Approximate KKT points and a proximity measure for termination
Karush-Kuhn-Tucker conditions in set optimization
Maximal margin classification for metric spaces
A New Sequential Optimality Condition for Constrained Optimization and Algorithmic Consequences
Asymptotic kuhn-tucker conditions in abstract spaces
On cone convexity of set-valued maps
Extensions of Asymptotic Kuhn–Tucker Conditions in Mathematical Programming
Data Mining
Asymptotic Lagrange Regularity for Pseudoconcave Programming with Weak Constraint Qualification
The Slacked Unconstrained Minimization Technique for Convex Programming
On sequential optimality conditions for smooth constrained optimization

This page was built for publication: Karush-Kuhn-Tucker conditions and Lagrangian approach for improving machine learning techniques: a survey and new developments