Gauge equivariant neural networks for quantum lattice gauge theories

@article{Luo2021GaugeEN,
  title={Gauge equivariant neural networks for quantum lattice gauge theories},
  author={Di Luo and Giuseppe Carleo and Bryan K. Clark and James Stokes},
  journal={Physical review letters},
  year={2021},
  volume={127 27},
  pages={
          276402
        }
}
Gauge symmetries play a key role in physics appearing in areas such as quantum field theories of the fundamental particles and emergent degrees of freedom in quantum materials. Motivated by the desire to efficiently simulate many-body quantum systems with exact local gauge invariance, gauge equivariant neural-network quantum states are introduced, which exactly satisfy the local Hilbert space constraints necessary for the description of quantum lattice gauge theory with Z_{d} gauge group and… 

Figures from this paper

Neural quantum states for supersymmetric quantum gauge theories
Supersymmetric quantum gauge theories are important mathematical tools in high energy physics. As an example, supersymmetric matrix models can be used as a holographic description of quantum black
Gauge covariant neural network for 4 dimensional non-abelian gauge theory
TLDR
A gauge covariant neural network for four dimensional non-abelian gauge theory, which realizes a map between rank-2 tensor valued vector fields, and the smeared force in hybrid Monte Carlo (HMC) is naturally derived with the backpropagation.
Scalars are universal: Gauge-equivariant machine learning, structured like classical physics
TLDR
It is shown that it is simple to parameterize universally approximating polynomial functions that are equivariant under these symmetries, or under the Euclidean, Lorentz, and Poincaré groups, at any dimensionality d.
Scalars are universal: Equivariant machine learning, structured like classical physics
TLDR
It is shown that it is simple to parameterize universally approximating polynomial functions that are equivariant under these symmetries, or under the Euclidean, Lorentz, and Poincaré groups, at any dimensionality d.
Infinite Neural Network Quantum States
TLDR
A general framework is developed for studying the gradient descent dynamics of neural network quantum states (NNQS), using a quantum state neural tangent kernel (QS-NTK) and an analytic solution is derived for quantum state supervised learning.
Geometric Deep Learning and Equivariant Neural Networks
TLDR
The mathematical foundations of geometric deep learning is surveyed, focusing on group equivariant and gaugeEquivariant neural networks and the use of Fourier analysis involving Wigner matrices, spherical harmonics and Clebsch–Gordan coefficients for G = SO(3), illustrating the power of representation theory for deep learning.
Learning quantum symmetries with interactive quantum-classical variational algorithms
TLDR
This paper develops a variational hybrid quantum-classical learning scheme to systematically probe for symmetries of | ψ (cid:105) with no a priori assumptions about the state and gives a less efficient algorithm with only local operations, which may be more appropriate for current noisy quantum devices.
Group Convolutional Neural Networks Improve Quantum State Accuracy
TLDR
G-CNNs achieve very good accuracy for Heisenberg quantum spin models in both ordered and spin liquid regimes, and improve the ground state accuracy on the triangular lattice over other variational Monte-Carlo methods.
Quantum computing hardware for HEP algorithms and sensing
Quantum information science harnesses the principles of quantum mechanics to realize computational algorithms with complexities vastly intractable by current computer platforms. Typical applications
Gauge Invariant Autoregressive Neural Networks for Quantum Lattice Models
TLDR
This paper presents a probabilistic procedure for estimating the response of the immune system to TSPs, a type of “spatially aggregating immune cell” that responds to Tau.
...
...

References

SHOWING 1-10 OF 47 REFERENCES
Review on novel methods for lattice gauge theories
TLDR
A review of the status and perspectives of new avenues for the exploration of lattice gauge theories based on quantum information ideas, which include tensor network calculations, quantum simulations with different physical platforms and quantum computations, and constitute nowadays a vibrant research area.
Lattice gauge equivariant convolutional neural networks
TLDR
It is demonstrated that L-CNNs can learn and generalize gauge invariant quantities that traditional convolutional neural networks are incapable of finding.
Diagnosing deconfinement and topological order
Topological or deconfined phases are characterized by emergent, weakly fluctuating, gauge fields. In condensed matter settings, they inevitably come coupled to excitations that carry the
Solving the quantum many-body problem with artificial neural networks
TLDR
A variational representation of quantum states based on artificial neural networks with a variable number of hidden neurons and a reinforcement-learning scheme that is capable of both finding the ground state and describing the unitary time evolution of complex interacting quantum systems.
Fermionic Quantum Computation
We define a model of quantum computation with local fermionic modes (LFMs)—sites which can be either empty or occupied by a fermion. With the standard correspondence between the Foch space of m LFMs
Efficient representation of quantum many-body states with deep neural networks
TLDR
A proof that, assuming a widely believed computational complexity conjecture, a deep neural network can efficiently represent most physical states, including the ground states of many-body Hamiltonians and states generated by quantum dynamics, while a shallow network representation with a restricted Boltzmann machine cannot efficiently represent some of those states.
Deep-neural-network solution of the electronic Schrödinger equation
TLDR
High-accuracy quantum chemistry methods struggle with a combinatorial explosion of Slater determinants in larger molecular systems, but now a method has been developed that learns electronic wavefunctions with deep neural networks and reaches high accuracy with only a few determinants.
Duality in Generalized Ising Models and Phase Transitions without Local Order Parameters
It is shown that any Ising model with positive coupling constants is related to another Ising model by a duality transformation. We define a class of Ising modelsMdn on d‐dimensional lattices
Neural-network quantum state tomography
TLDR
It is demonstrated that machine learning allows one to reconstruct traditionally challenging many-body quantities—such as the entanglement entropy—from simple, experimentally accessible measurements, and can benefit existing and future generations of devices.
...
...