Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows
arXiv:2001.00585
Abstract
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.
16 pages, 7 figures
References in corpus (18)
- Adam: A Method for Stochastic Optimization
- Quantum Machine Learning
- Solving the Quantum Many-Body Problem with Artificial Neural Networks
- Adiabatic Quantum Computing
- Machine learning phases of matter
- Density estimation using Real NVP
- Spin-Glass Theory for Pedestrians
- Self-Learning Monte Carlo Method
- Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
- Computational Role of Multiqubit Tunneling in a Quantum Annealer
- Flow-based generative models for Markov chain Monte Carlo in lattice field theory
- An exact mapping between the Variational Renormalization Group and Deep Learning
- Neural Network Renormalization Group
- Replica Symmetry Breaking in Bipartite Spin Glasses and Neural Networks
- Simulating the Ising Model with a Deep Convolutional Generative Adversarial Network
- Integer Discrete Flows and Lossless Compression
- The Renormalization Group for Disordered Systems
- A Probability Density Theory for Spin-Glass Systems