A Probability Density Theory for Spin-Glass Systems
arXiv:2001.00927
Abstract
Spin-glass systems are universal models for representing many-body phenomena in statistical physics and computer science. High quality solutions of NP-hard combinatorial optimization problems can be encoded into low energy states of spin-glass systems. In general, evaluating the relevant physical and computational properties of such models is difficult due to critical slowing down near a phase transition. Ideally, one could use recent advances in deep learning for characterizing the low-energy properties of these complex systems. Unfortunately, many of the most promising machine learning approaches are only valid for distributions over continuous variables and thus cannot be directly applied to discrete spin-glass models. To this end, we develop a continuous probability density theory for spin-glass systems with arbitrary dimensions, interactions, and local fields. We show how our formulation geometrically encodes key physical and computational properties of the spin-glass in an instance-wise fashion without the need for quenched disorder averaging. We show that our approach is beyond the mean-field theory and identify a transition from a convex to non-convex energy landscape as the temperature is lowered past a critical temperature. We apply our formalism to a number of spin-glass models including the Sherrington-Kirkpatrick (SK) model, spins on random Erdős-Rényi graphs, and random restricted Boltzmann machines.
arXiv comment20 pages, 5 figures
References in corpus (12)
- Density estimation using Real NVP
- Spin-Glass Theory for Pedestrians
- Self-Learning Monte Carlo Method
- Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
- Flow-based generative models for Markov chain Monte Carlo in lattice field theory
- Neural Network Renormalization Group
- Thermodynamics of Restricted Boltzmann Machines and related learning dynamics
- Spectral Dynamics of Learning Restricted Boltzmann Machines
- Replica Symmetry Breaking in Bipartite Spin Glasses and Neural Networks
- Role of the Tracy-Widom distribution in the finite-size fluctuations of the critical temperature of the Sherrington-Kirkpatrick spin glass
- Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows
- On a "continuum" formulation of the Ising model partition function