Model-Based and Sample-Efficient AI-Assisted Math Discovery in Sphere Packing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tutunov, Rasul, Maraval, Alexandre, Grosnit, Antoine, Li, Xihan, Wang, Jun, Bou-Ammar, Haitham
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909949048651776
author Tutunov, Rasul
Maraval, Alexandre
Grosnit, Antoine
Li, Xihan
Wang, Jun
Bou-Ammar, Haitham
author_facet Tutunov, Rasul
Maraval, Alexandre
Grosnit, Antoine
Li, Xihan
Wang, Jun
Bou-Ammar, Haitham
contents Sphere packing, Hilbert's eighteenth problem, asks for the densest arrangement of congruent spheres in n-dimensional Euclidean space. Although relevant to areas such as cryptography, crystallography, and medical imaging, the problem remains unresolved: beyond a few special dimensions, neither optimal packings nor tight upper bounds are known. Even a major breakthrough in dimension $n=8$, later recognised with a Fields Medal, underscores its difficulty. A leading technique for upper bounds, the three-point method, reduces the problem to solving large, high-precision semidefinite programs (SDPs). Because each candidate SDP may take days to evaluate, standard data-intensive AI approaches are infeasible. We address this challenge by formulating SDP construction as a sequential decision process, the SDP game, in which a policy assembles SDP formulations from a set of admissible components. Using a sample-efficient model-based framework that combines Bayesian optimisation with Monte Carlo Tree Search, we obtain new state-of-the-art upper bounds in dimensions $4-16$, showing that model-based search can advance computational progress in longstanding geometric problems. Together, these results demonstrate that sample-efficient, model-based search can make tangible progress on mathematically rigid, evaluation limited problems, pointing towards a complementary direction for AI-assisted discovery beyond large-scale LLM-driven exploration.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04829
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Model-Based and Sample-Efficient AI-Assisted Math Discovery in Sphere Packing
Tutunov, Rasul
Maraval, Alexandre
Grosnit, Antoine
Li, Xihan
Wang, Jun
Bou-Ammar, Haitham
Artificial Intelligence
Sphere packing, Hilbert's eighteenth problem, asks for the densest arrangement of congruent spheres in n-dimensional Euclidean space. Although relevant to areas such as cryptography, crystallography, and medical imaging, the problem remains unresolved: beyond a few special dimensions, neither optimal packings nor tight upper bounds are known. Even a major breakthrough in dimension $n=8$, later recognised with a Fields Medal, underscores its difficulty. A leading technique for upper bounds, the three-point method, reduces the problem to solving large, high-precision semidefinite programs (SDPs). Because each candidate SDP may take days to evaluate, standard data-intensive AI approaches are infeasible. We address this challenge by formulating SDP construction as a sequential decision process, the SDP game, in which a policy assembles SDP formulations from a set of admissible components. Using a sample-efficient model-based framework that combines Bayesian optimisation with Monte Carlo Tree Search, we obtain new state-of-the-art upper bounds in dimensions $4-16$, showing that model-based search can advance computational progress in longstanding geometric problems. Together, these results demonstrate that sample-efficient, model-based search can make tangible progress on mathematically rigid, evaluation limited problems, pointing towards a complementary direction for AI-assisted discovery beyond large-scale LLM-driven exploration.
title Model-Based and Sample-Efficient AI-Assisted Math Discovery in Sphere Packing
topic Artificial Intelligence
url https://arxiv.org/abs/2512.04829