Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows

01/02/2020
by   Gavin S. Hartnett, et al.
0

Spin-glasses are universal models that can capture complex behavior of many-body systems at the interface of statistical physics and computer science including discrete optimization, inference in graphical models, and automated reasoning. Computing the underlying structure and dynamics of such complex systems is extremely difficult due to the combinatorial explosion of their state space. Here, we develop deep generative continuous spin-glass distributions with normalizing flows to model correlations in generic discrete problems. We use a self-supervised learning paradigm by automatically generating the data from the spin-glass itself. We demonstrate that key physical and computational properties of the spin-glass phase can be successfully learned, including multi-modal steady-state distributions and topological structures among metastable states. Remarkably, we observe that the learning itself corresponds to a spin-glass phase transition within the layers of the trained normalizing flows. The inverse normalizing flows learns to perform reversible multi-scale coarse-graining operations which are very different from the typical irreversible renormalization group techniques.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/03/2020

A Probability Density Theory for Spin-Glass Systems

Spin-glass systems are universal models for representing many-body pheno...
research
03/27/2023

On the stepwise nature of self-supervised learning

We present a simple picture of the training process of self-supervised l...
research
12/27/2022

GEDI: GEnerative and DIscriminative Training for Self-Supervised Learning

Self-supervised learning is a popular and powerful method for utilizing ...
research
12/23/2021

Physics Constrained Flow Neural Network for Short-Timescale Predictions in Data Communications Networks

Machine learning is gaining growing momentum in various recent models fo...
research
06/06/2021

Self-supervised Rubik's Cube Solver

This work demonstrates that deep neural networks (DNNs) can solve a comb...
research
06/27/2023

Deep Normalizing Flows for State Estimation

Safe and reliable state estimation techniques are a critical component o...
research
07/05/2023

ν^2-Flows: Fast and improved neutrino reconstruction in multi-neutrino final states with conditional normalizing flows

In this work we introduce ν^2-Flows, an extension of the ν-Flows method ...

Please sign up or login with your details

Forgot password? Click here to reset