Optimization of the Sherrington-Kirkpatrick Hamiltonian

Let A be a symmetric random matrix with independent and identically distributed Gaussian entries above the diagonal. We consider the problem of maximizing the quadratic form associated to A over binary vectors. In the language of statistical physics, this amounts to finding the ground state of the S...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings / annual Symposium on Foundations of Computer Science s. 1417 - 1433
Hlavní autor: Montanari, Andrea
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.11.2019
Témata:
Approximation algorithms
Complexity theory
Glass
Message passing
message passing algorithms
Optimization
Physics
replica symmetry breaking
Sherrington-Kirkpatrick
Signal processing algorithms
spin glasses
ISSN:2575-8454
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Let A be a symmetric random matrix with independent and identically distributed Gaussian entries above the diagonal. We consider the problem of maximizing the quadratic form associated to A over binary vectors. In the language of statistical physics, this amounts to finding the ground state of the Sherrington-Kirkpatrick model of spin glasses. The asymptotic value of this optimization problem was characterized by Parisi via a celebrated variational principle, subsequently proved by Talagrand. We give an algorithm that, for any ε > 0, outputs a feasible solution whose value is at least (1 - ε) of the optimum, with probability converging to one as the dimension n of the matrix diverges. The algorithm's time complexity is of order n 2 . It is a message-passing algorithm, but the specific structure of its update rules is new. As a side result, we prove that, at (low) non-zero temperature, the algorithm constructs approximate solutions of the Thouless-Anderson-Palmer equations.
ISSN:2575-8454
DOI:10.1109/FOCS.2019.00087