arXiv · 2604.11101
Generating Hadamard matrices with transformers
Abstract
We present a new method for constructing Hadamard matrices that combines transformer neural networks with local search in the PatternBoost framework. Our approach is designed for extremely sparse combinatorial search problems and is particularly effective for Hadamard matrices of Goethals--Seidel type, where Fourier methods permit fast scoring and optimisation. For orders between 100 and 200, it produces large numbers of inequivalent Hadamard matrices, and for larger orders, it succeeds where local search from random initialisation fails. The largest example found by our method has order 252. In addition to these new constructions, our experiments reveal that the transformer can discover and exploit useful hidden symmetry in the search space.
Explore related subjects
Keep this discovery
Geordie Williamson, Oded Yacobi, Paul Zinn-Justin. 2026-04-13. Generating Hadamard matrices with transformers. https://arxiv.org/abs/2604.11101
Cite the original work for its findings. Save a collection to share your selection of sources.