Work

TransOpt: Transformer-based Representation Learning for Optimization Problem Classification

Year: 2023

Type: preprint

Abstract: We propose a representation of optimization problem instances using a transformer-based neural network architecture trained for the task of problem classification of the 24 problem classes from the Black-box Optimization Benchmarking (BBOB) benchmark. We show that transformer-based methods can be trained to recognize problem classes with accuracies in the range of 70\%-80\% for different problem dimensions, suggesting the possible application of transformer architectures in acquiring representations for black-box optimization problems.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2311.18035

Authors: Cenikj, Gjorgjina, Petelin, Gašper, Eftimov, Tome

Language: English

Topic: Metaheuristic Optimization Algorithms Research

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Javna Agencija za Raziskovalno Dejavnost RS

Awards: G1226906449, G6508940539, Representation Learning of Landscape Spaces for Explainable Performance of Stochastic Optimization Algorithms, Auto-OPT: Automated selection and configuration of single-objective continuous optimization algorithms, Computer Structures and Systems

OpenAlex ID: W4389260665

Cites:

Cited by: 3

Related to: 10