NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems (2021-12-20T00:00:00.000000Z)

TL;DR

The most significant new feature is the possibility to define arbitrary neural network ansätze in pure Python code using the concise notation of machine-learning frameworks, which allows for just-in-time compilation as well as the implicit generation of gradients thanks to automatic differentiation.

Abstract

We introduce version 3 of NetKet, the machine learning toolbox for many-body quantum physics. NetKet is built around neural quantum states and provides efficient algorithms for their evaluation and optimization. This new version is built on top of JAX, a differentiable programming and accelerated linear algebra framework for the Python programming language. The most significant new feature is the possibility to define arbitrary neural network ansätze in pure Python code using the concise notation of machine-learning frameworks, which allows for just-in-time compilation as well as the implicit generation of gradients thanks to automatic differentiation. NetKet 3 also comes with support for GPU and TPU accelerators, advanced support for discrete symmetry groups, chunking to scale up to thousands of degrees of freedom, drivers for quantum dynamics applications, and improved modularity, allowing users to use only parts of the toolbox as a foundation for their own code.

Authors

Filippo Vicentini

1 papers

Damian Hofmann

1 papers

A. Szab'o

1 papers

TL;DR

Abstract

Authors

References99 items

Variational solutions to fermion-to-qubit mappings in two spatial dimensions

Numerical and geometrical aspects of flow-based variational quantum Monte Carlo

Accuracy of restricted Boltzmann machines for the one-dimensional $J_1-J_2$ Heisenberg model

Neural-Network Quantum States for Periodic Systems in Continuous Space

mpi4jax: Zero-copy MPI communication of JAX arrays

jVMC: Versatile and performant variational Monte Carlo leveraging automated differentiation and GPU acceleration

Role of stochastic noise and generalization error in the time propagation of neural-network quantum states

Many-body quantum states with exact conservation of non-Abelian and lattice symmetries through variational Monte Carlo

Group Convolutional Neural Networks Improve Quantum State Accuracy

Supermagnonic Propagation in Two-Dimensional Antiferromagnets.

Broken-Symmetry Ground States of the Heisenberg Model on the Pyrochlore Lattice

Expressive power of complex-valued restricted Boltzmann machines for solving nonstoquastic Hamiltonians

Learning the ground state of a non-stoquastic quantum Hamiltonian in a rugged neural network landscape

Helping restricted Boltzmann machines with quantum-state representation by restoring symmetry

Dirac-Type Nodal Spin Liquid Revealed by Refined Quantum Many-Body Solver Using Neural-Network Wave Function, Correlation Ratio, and Level Spectroscopy

Dirac-type nodal spin liquid revealed by machine learning

Gapless spin liquid and valence-bond solid in the J1 - J2 Heisenberg model on the square lattice: Insights from singlet and triplet excitations

A Survey of the Usages of Deep Learning for Natural Language Processing

Neural network wave functions and the sign problem

Real time evolution with neural-network quantum states

Quantum Many-Body Dynamics in Two Dimensions with Artificial Neural Networks.

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Summarizing CPU and GPU Design Trends with Product Data

SLATE: Design of a Modern Distributed and Accelerated Linear Algebra Library

Geometry of learning neural quantum states

Quantum Natural Gradient

Restricted Boltzmann Machines for Quantum States with Non-Abelian or Anyonic Symmetries.

NetKet: A machine learning toolkit for many-body quantum systems

Machine learning and the physical sciences

Investigating ultrafast quantum magnetism with machine learning

Variational Neural-Network Ansatz for Steady States in Open Quantum Systems.

Variational Quantum Monte Carlo Method with a Neural-Network Ansatz for Open Quantum Systems.

Neural-Network Approach to Dissipative Quantum Many-Body Dynamics.

Deep autoregressive models for the efficient variational simulation of many-body quantum systems

Theory of variational quantum simulation

Solving Statistical Mechanics using Variational Autoregressive Networks

Neural-network states for the classical simulation of quantum computing

Symmetries and Many-Body Excitations with Neural-Network Quantum States.

This looks like that: deep learning for interpretable image recognition

Quenches near Ising quantum criticality as a challenge for artificial neural networks

Neural-network Quantum States

Latent Space Purification via Neural Density Operators.

Quantum Monte Carlo Approaches for Correlated Systems

OpenFermion: the electronic structure package for quantum computers

Chiral topological phases from artificial neural networks

Neural-Network Quantum States, String-Bond States, and Chiral Topological States

Neural-network quantum state tomography

Deep Sets

Quantum Entanglement in Neural Network States

Solving the quantum many-body problem with artificial neural networks

Group Equivariant Convolutional Networks

Numba: a LLVM-based Python JIT compiler

On the geometry of mixed states and the Fisher information tensor

One-Dimensional Liquid ^{4}He: Dynamical Properties beyond Luttinger-Liquid Theory.

Julia: A Fresh Approach to Numerical Computing

Variational principle for steady states of dissipative quantum many-body systems.

ImageNet classification with deep convolutional neural networks

QuTiP 2: A Python framework for the dynamics of open quantum systems

Parallel solution of partial symmetric eigenvalue problems from electronic structure calculations

QuTiP: An open-source Python framework for the dynamics of open quantum systems

Localization and Glassy Dynamics Of Many-Body Quantum Systems

On the Eigenfunctions of Many-Particle Systems in Quantum Mechanics

Time-dependent variational principle for quantum lattices.

The Complex Gradient Operator and the CR-Calculus ECE275A - Lecture Supplement - Fall 2005

The Theory of Open Quantum Systems

Introduction to Numerical Analysis

GREEN FUNCTION MONTE CARLO WITH STOCHASTIC RECONFIGURATION

Natural Gradient Works Efficiently in Learning

ScaLAPACK: a scalable linear algebra library for distributed memory concurrent computers

Simple variational wave functions for two-dimensional Heisenberg spin-(1/2 antiferromagnets.

Geometry of the Time-Dependent Variational Principle in Quantum Mechanics

An accurate intermolecular potential for argon

Completely positive linear maps on complex matrices

Linear transformations which preserve trace and positive semidefiniteness of operators

Computing irreducible representations of groups

Monte Carlo Sampling Methods Using Markov Chains and Their Applications