Combinatorial optimization with physics-inspired graph neural networks

Combinatorial optimization problems are pervasive across science and industry. Modern deep learning tools are poised to solve these problems at unprecedented scales, but a unifying framework that incorporates insights from statistical physics is still outstanding. Here we demonstrate how graph neura...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Nature machine intelligence 2022-04, Vol.4 (4), p.367-377
Hauptverfasser:	Schuetz, Martin J. A., Brubaker, J. Kyle, Katzgraber, Helmut G.
Format:	Artikel
Sprache:	eng
Schlagworte:	4000/4011 639/705/117 639/766/483/481 639/766/530/2804 Algorithms Combinatorial analysis Deep learning Engineering Graph neural networks Heuristic Ising model Machine learning Neural networks Optimization Optimization techniques Physics Polynomials Robustness (mathematics) Solvers Spin glasses Variables
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!