cond-mat.str-elcond-mat.mtrl-scics.LGphysics.chem-ph

Self-attention is a Dyson equation for many-body machine learning

📅 👥 1 authors arXiv:2611.21398v1

Authors

Abstract

Why does symmetric sum-pooling (DeepSets) predict ground-state potentials to sub-meV accuracy, yet fail for correlated wavefunctions and excited states? Sum-pooling is a mean-field (Hartree) model: its $O(1/N)$ off-diagonal Jacobian suffices for nearsighted ground-state energies, but erases nonlocal two-body correlations. We show that self-attention is a real-space Dyson iteration whose Boltzmann (softmax) kernel acts as a two-body self-energy. Because physical Hamiltonians act pairwise, Löwdin's 2-RDM theorem and the Galitskii--Migdal relation guarantee that iterating a two-body propagator captures the full energetics of correlated matter. When fitting a fractal backflow determinant, DeepSets blurs the nodal surface onto a mean-field envelope, whereas self-attention recovers the fractal attractor. Seen through this lens, the unreasonable effectiveness of attention is not an accident; in a universe built from pairwise interactions, two-body attention is all you need.

Paper Information

arXiv ID:
2611.21398v1
Published:

Related Categories

cond-mat.str-elcond-mat.mtrl-scics.LGphysics.chem-ph