High generalization performance structured self-attention model for knapsack problem

DOI10.1142/S1793830921500762MaRDI QIDQ5025155

Tian-de Guo, Man Ding, Cong-Ying Han

Publication date: 1 February 2022

Published in: Discrete Mathematics, Algorithms and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s1793830921500762

zbMATH Keywords

knapsack problem; generalization performance; deep reinforcement learning; self-attention

Mathematics Subject Classification ID

68T07: Artificial neural networks and deep learning

90C27: Combinatorial optimization

Uses Software

• Gurobi
• PyTorch
• ImageNet
• AdaGrad
• Tensor2Tensor
• GNMT
• AlexNet

Cites Work

• Unnamed Item
• An adaptive stochastic knapsack problem
• ``Neural computation of decisions in optimization problems
• A genetic algorithm for the multidimensional knapsack problem
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Machine learning for combinatorial optimization: a methodological tour d'horizon
• Advanced greedy algorithms and surrogate constraint methods for linear and quadratic knapsack and covering problems
• Backtracking search optimization algorithm for numerical optimization problems
• A knapsack-type public key cryptosystem based on arithmetic in finite fields
• Market Split and Basis Reduction: Towards a Solution of the Cornuéjols-Dawande Instances
• Discrete-Variable Extremum Problems
• Branch-and-Bound Methods: A Survey
• Solving Combinatorial Problems with Machine Learning Methods