Towards Utilitarian Combinatorial Assignment with Deep Neural Networks\n and Heuristic Algorithms

2021/07/01 by Fredrik Präntare, Präntare, Fredrik, Mattias Tiger +7
Computer Science · Decision Sciences · Engineering · #Artificial Intelligence (cs.AI) #Constraint Satisfaction and Optimization #FOS: Computer and information sciences #Optimization and Packing Problems #Scheduling and Timetabling Solutions #Vehicle Routing Optimization Methods

paper · pdf · doi:10.48550/arxiv.2107.00317

openalex publication_date 2021/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents preliminary work on using deep neural networks to guide\ngeneral-purpose heuristic algorithms for performing utilitarian combinatorial\nassignment. In more detail, we use deep learning in an attempt to produce\nheuristics that can be used together with e.g., search algorithms to generate\nfeasible solutions of higher quality more quickly. Our results indicate that\nour approach could be a promising future method for constructing such\nheuristics.\n

Citations

• Algorithm for optimal winner determination in combinatorial auctions
• Learning a SAT Solver from Single-Bit Supervision

Related

• Neural Combinatorial Optimization: a New Player in the Field
• Neural Algorithmic Reasoning for Combinatorial Optimisation
• How Good Is Neural Combinatorial Optimization? A Systematic Evaluation on the Traveling Salesman Problem
• COMBHelper: A Neural Approach to Reduce Search Space for Graph Combinatorial Problems
• On the Generalization of Neural Combinatorial Optimization Heuristics