Efficient learning of ground & thermal states within phases of matter

Abstract

We consider two related tasks: (a) estimating a parameterisation of a given Gibbs state and expectation values of Lipschitz observables on this state; and (b) learning the expectation values of local observables within a thermal or quantum phase of matter. In both cases, we wish to minimise the number of samples we use to learn these properties to a given precision. For the first task, we develop new techniques to learn parameterisations of classes of systems, including quantum Gibbs states of non-commuting Hamiltonians with exponential decay of correlations and the approximate Markov property. We show it is possible to infer the expectation values of all extensive properties of the state from a number of copies that not only scales polylogarithmically with the system size, but polynomially in the observable's locality -- an exponential improvement. This set of properties includes expected values of quasi-local observables and entropies. For the second task, we develop efficient algorithms for learning observables in a phase of matter of a quantum system. By exploiting the locality of the Hamiltonian, we show that $M$ local observables can be learned with probability $1-\delta$ to precision $\epsilon$ with using only $N=O\left(\log \right(\frac{M}{\delta }\left)e^{polylog({\epsilon }^{-1})}\right)$ samples -- an exponential improvement on the precision over previous bounds. Our results apply to both families of ground states of Hamiltonians displaying local topological quantum order, and thermal phases of matter with exponential decay of correlations. In addition, our sample complexity applies to the worse case setting whereas previous results only applied on average. Furthermore, we develop tools of independent interest, such as robust shadow tomography algorithms, Gibbs approximations to ground states, and generalisations of transportation cost inequalities for Gibbs states.

arXiv comment45 pages, 1 figure. This is a coordinated posting with similar work by Lewis, Tran, Lehner, Kueng, Huang, and Preskill. See their paper in the same arXiv listing as this one

References in corpus (24)

• Machine learning phases of matter
• Lieb-Robinson bounds and the generation of correlations and topological quantum order
• Provably efficient machine learning for quantum many-body problems
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• A short proof of stability of topological order under local perturbations
• Stability of Frustration-Free Hamiltonians
• Sample-optimal tomography of quantum states
• Lieb-Robinson Bound and Locality for General Markovian Quantum Dynamics
• Quantum Belief Propagation
• Machine learning of quantum phase transitions
• On Variational Expressions for Quantum Relative Entropies
• Clustering of conditional mutual information for quantum Gibbs states above a threshold temperature
• Locality in Quantum Systems
• Lieb-Robinson bounds and the simulation of time evolution of local observables in lattice systems
• Improved machine learning algorithm for predicting ground state properties
• Purifying Deep Boltzmann Machines for Thermal Quantum States
• Classical algorithms, correlation decay, and complex zeros of partition functions of quantum many-body systems
• On the complexity of quantum partition functions
• Exponential decay of mutual information for Gibbs states of local Hamiltonians
• Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models
• Fisher zeros and correlation decay in the Ising model
• Quantum concentration inequalities
• Efficient quantum tomography
• Decay of quantum conditional mutual information for purely generated finitely correlated states

Cited by in corpus (2)

• Improved machine learning algorithm for predicting ground state properties
• On the Sample Complexity of Quantum Boltzmann Machine Learning