Provable learning of quantum states with graphical models

• URL: http://arxiv.org/abs/2309.09235v1
• Date: Sun, 17 Sep 2023 10:36:24 GMT
• Title: Provable learning of quantum states with graphical models
• Authors: Liming Zhao, Naixu Guo, Ming-Xing Luo and Patrick Rebentrost
• Abstract summary: We show that certain quantum states can be learned with a sample complexity textitexponentially better than naive tomography. Our results allow certain quantum states to be learned with a sample complexity textitexponentially better than naive tomography.
• Score: 4.004283689898333
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The complete learning of an $n$-qubit quantum state requires samples exponentially in $n$. Several works consider subclasses of quantum states that can be learned in polynomial sample complexity such as stabilizer states or high-temperature Gibbs states. Other works consider a weaker sense of learning, such as PAC learning and shadow tomography. In this work, we consider learning states that are close to neural network quantum states, which can efficiently be represented by a graphical model called restricted Boltzmann machines (RBMs). To this end, we exhibit robustness results for efficient provable two-hop neighborhood learning algorithms for ferromagnetic and locally consistent RBMs. We consider the $L_p$-norm as a measure of closeness, including both total variation distance and max-norm distance in the limit. Our results allow certain quantum states to be learned with a sample complexity \textit{exponentially} better than naive tomography. We hence provide new classes of efficiently learnable quantum states and apply new strategies to learn them.

Related papers

• Optimizing random local Hamiltonians by dissipation [44.99833362998488]
  We prove that a simplified quantum Gibbs sampling algorithm achieves a $Omega(frac1k)$-fraction approximation of the optimum. Our results suggest that finding low-energy states for sparsified (quasi)local spin and fermionic models is quantumly easy but classically nontrivial.
  arXiv  Detail & Related papers  (2024-11-04T20:21:16Z)
• Learning topological states from randomized measurements using variational tensor network tomography [0.4818215922729967]
  Learning faithful representations of quantum states is crucial to fully characterizing the variety of many-body states created on quantum processors. We implement and study a tomographic method that combines variational optimization on tensor networks with randomized measurement techniques. We demonstrate its ability to learn the ground state of the surface code Hamiltonian as well as an experimentally realizable quantum spin liquid state.
  arXiv  Detail & Related papers  (2024-05-31T21:05:43Z)
• Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms [48.869199703062606]
  A fundamental problem in quantum many-body physics is that of finding ground states of local Hamiltonians. We introduce two approaches that achieve a constant sample complexity, independent of system size $n$, for learning ground state properties.
  arXiv  Detail & Related papers  (2024-05-28T18:00:32Z)
• Efficient learning of quantum states prepared with few fermionic non-Gaussian gates [0.0]
  We present an efficient algorithm for learning states on $n$ fermion modes prepared by any number of Gaussian gates. Our work sheds light on the structure of states prepared with few non-Gaussian gates and offers an improved upper bound on their circuit complexity.
  arXiv  Detail & Related papers  (2024-02-28T19:18:27Z)
• Classical shadow tomography for continuous variables quantum systems [13.286165491120467]
  We introduce two experimentally realisable schemes for obtaining classical shadows of CV quantum states. We are able to overcome new mathematical challenges due to the infinite-dimensionality of CV systems. We provide a scheme to learn nonlinear functionals of the state, such as entropies over any small number of modes.
  arXiv  Detail & Related papers  (2022-11-14T17:56:29Z)
• Quantum state tomography with tensor train cross approximation [84.59270977313619]
  We show that full quantum state tomography can be performed for such a state with a minimal number of measurement settings. Our method requires exponentially fewer state copies than the best known tomography method for unstructured states and local measurements.
  arXiv  Detail & Related papers  (2022-07-13T17:56:28Z)
• A quantum algorithm for training wide and deep classical neural networks [72.2614468437919]
  We show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We numerically demonstrate that the MNIST image dataset satisfies such conditions. We provide empirical evidence for $O(log n)$ training of a convolutional neural network with pooling.
  arXiv  Detail & Related papers  (2021-07-19T23:41:03Z)
• Private learning implies quantum stability [5.435793655810987]
  Learning an unknown $n$-qubit quantum state $rho$ is a fundamental challenge in quantum computing. We prove a sequence of (information-theoretic) implications from differentially-private PAC learning, to communication complexity, to online learning and then to quantum stability.
  arXiv  Detail & Related papers  (2021-02-14T15:13:25Z)
• Efficient Verification of Anticoncentrated Quantum States [0.38073142980733]
  I present a novel method for estimating the fidelity $F(mu,tau)$ between a preparable quantum state $mu$ and a classically specified target state $tau$. I also present a more sophisticated version of the method, which uses any efficiently preparable and well-characterized quantum state as an importance sampler.
  arXiv  Detail & Related papers  (2020-12-15T18:01:11Z)
• Neural network quantum state tomography in a two-qubit experiment [52.77024349608834]
  Machine learning inspired variational methods provide a promising route towards scalable state characterization for quantum simulators. We benchmark and compare several such approaches by applying them to measured data from an experiment producing two-qubit entangled states. We find that in the presence of experimental imperfections and noise, confining the variational manifold to physical states greatly improves the quality of the reconstructed states.
  arXiv  Detail & Related papers  (2020-07-31T17:25:12Z)
• Quantum Gram-Schmidt Processes and Their Application to Efficient State Read-out for Quantum Algorithms [87.04438831673063]
  We present an efficient read-out protocol that yields the classical vector form of the generated state. Our protocol suits the case that the output state lies in the row space of the input matrix. One of our technical tools is an efficient quantum algorithm for performing the Gram-Schmidt orthonormal procedure.
  arXiv  Detail & Related papers  (2020-04-14T11:05:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.