Institute for Condensed Matter Theory Seminar: "Variational Neural Annealing"
(sign-up)Juan Carrisquilla, Vector Institute, Canada
|Event Contact:||Janice Benner
|Sponsor:||The Physics Department & The Institute for Condensed Matter Theory|
Many important challenges in science and technology can be cast as optimization problems. When viewed in a statistical physics framework, these can be tackled by simulated annealing, where a gradual cooling procedure helps search for ground state solutions of a target Hamiltonian. While powerful, simulated annealing is known to have prohibitively slow sampling dynamics when the optimization landscape is rough or glassy. In this seminar I will show that by generalizing the target distribution with a parameterized model, an analogous annealing framework based on the variational principle can be used to search for ground state solutions. Autoregressive models such as recurrent neural networks provide ideal parameterizations since they can be exactly sampled without slow dynamics even when the model encodes a rough landscape. We implement this procedure in the classical and quantum settings on several prototypical spin glass Hamiltonians, and find that it significantly outperforms traditional simulated annealing in the asymptotic limit, illustrating the potential power
To request disability-related accommodations for this event, please contact the person listed above, or the unit hosting the event.
Event Mailing List
Receive Illinois Physics events weekly in your inbox.