Condensed Matter · 2022 · 15 citations · 31 references
Natural SciencesComputer SciencePhysicsComputational PhysicsDynamical SystemsMachine LearningChaos TheoryNeural NetworksQuantum ComputationQuantum DynamicsAnnealingChaotic DynamicsGlassy DynamicsQuantum Many-body Systems
Artificial neural networks have been widely adopted as ansatzes to study classical and quantum systems. However, for some notably hard systems, such as those exhibiting glassiness and frustration, they have mainly achieved unsatisfactory results, despite their representational power and entanglement content, thus suggesting a potential conservation of computational complexity in the learning process. We explore this possibility by implementing the neural annealing method with autoregressive neural networks on a model that exhibits glassy and fractal dynamics: the two-dimensional Newman–Moore model on a triangular lattice. We find that the annealing dynamics is globally unstable because of highly chaotic loss landscapes. Furthermore, even when the correct ground-state energy is found, the neural network generally cannot find degenerate ground-state configurations due to mode collapse. These findings indicate that the glassy dynamics exhibited by the Newman–Moore model caused by the presence of fracton excitations in the configurational space likely manifests itself through trainability issues and mode collapse in the optimization landscape.
31
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Optimization by Simulated Annealing
Scott Kirkpatrick, C. D. Gelatt, M.P. Vecchi · Science · 1983 · 44.6K citations
Machine learning and the physical sciences
Giuseppe Carleo, K. Cranmer, Laurent Daudet et al. · Reviews of Modern Physics · 2019 · 2.4K citations · Full text
Solving the quantum many-body problem with artificial neural networks
Giuseppe Carleo, Matthias Troyer · Science · 2017 · 2.2K citations · Full text
Machine learning phases of matter
Juan Carrasquilla, Roger G. Melko · Nature Physics · 2017 · 1.5K citations · Full text