Heuristics to convex quadratic knapsack problems in sorted ADP

Authors:
Bin Zhang;Zhongsheng Hua
Affiliations:
School of Management, University of Science & Technology of China, Hefei, Anhui, People’s Republic of China;School of Management, University of Science & Technology of China, Hefei, Anhui, People’s Republic of China
Venue:
ICIC'06 Proceedings of the 2006 international conference on Intelligent Computing - Volume Part I
Year:
2006

Citing 3
Cited 0

Formulations and valid inequalities for the node capacitated graph partitioning problem

Mathematical Programming: Series A and B
Introduction to Dynamic Programming

Introduction to Dynamic Programming
An approximate dynamic programming approach to convex quadratic knapsack problems

Computers and Operations Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

Approximate dynamic programming (ADP) was developed for solving large-scale optimization problems, and function approximation is an important method in the dynamic programming scheme. Continuous quadratic programming relaxation (CQPR) and the integral parts of the solutions to CQPR are two intuitionistic heuristics as function approximations in ADP for solving quadratic knapsack problems (QKPs). We propose a rule of ordering variables to sort the first variable to be solved in ADP, and develop a heuristic which adaptively fixes the variables according to the solution to CQPR of convex QKPs based the rule. By using the rule and heuristics, we propose a sorted ADP heuristic scheme for QKPs.