High generalization performance structured self-attention model for knapsack problem

DOI10.1142/S1793830921500762MaRDI QIDQ5025155zbMATH OpenOpenAlexFDO

Authors Man Ding, Congying Han, Tiande Guo

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 problemgeneralization performancedeep reinforcement learningself-attention

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Combinatorial optimization (90C27)

Recommendations

• Reinforcement learning for the knapsack problem
• Architecture self-attention mechanism: nonlinear optimization for neural architecture search
• Fast algorithms for knapsack via convolution and prediction
• An attention algorithm for solving large scale structured \(l_0\)-norm penalty estimation problems
• scientific article; zbMATH DE number 2202239
• Generalized attention-weighted reinforcement learning
• scientific article; zbMATH DE number 2086191
• Attention-Gated Reinforcement Learning of Internal Representations for Classification
• Learning generalized strong branching for set covering, set packing, and 0-1 knapsack problems

Cites work

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

Cited in

(3)

• NeuroPrim: an attention-based model for solving NP-hard spanning tree problems
• Optimal pivot path of the simplex method for linear programming based on reinforcement learning
• A \(K\)-means supported reinforcement learning framework to multi-dimensional knapsack

Describes a project that uses

Uses Software

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

This page was built for publication: High generalization performance structured self-attention model for knapsack problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5025155)