Protocols for Trainable and Differentiable Quantum Generative Modelling
- URL: http://arxiv.org/abs/2202.08253v1
- Date: Wed, 16 Feb 2022 18:55:48 GMT
- Title: Protocols for Trainable and Differentiable Quantum Generative Modelling
- Authors: Oleksandr Kyriienko, Annie E. Paine, Vincent E. Elfving
- Abstract summary: We propose an approach for learning probability distributions as differentiable quantum circuits (DQC)
We perform training of a DQC-based model, where data is encoded in a latent space with a phase feature map, followed by a variational quantum circuit.
This allows fast sampling from parametrized distributions using a single-shot readout.
- Score: 21.24186888129542
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose an approach for learning probability distributions as
differentiable quantum circuits (DQC) that enable efficient quantum generative
modelling (QGM) and synthetic data generation. Contrary to existing QGM
approaches, we perform training of a DQC-based model, where data is encoded in
a latent space with a phase feature map, followed by a variational quantum
circuit. We then map the trained model to the bit basis using a fixed unitary
transformation, coinciding with a quantum Fourier transform circuit in the
simplest case. This allows fast sampling from parametrized distributions using
a single-shot readout. Importantly, simplified latent space training provides
models that are automatically differentiable, and we show how samples from
distributions propagated by stochastic differential equations (SDEs) can be
accessed by solving stationary and time-dependent Fokker-Planck equations with
a quantum protocol. Finally, our approach opens a route to multidimensional
generative modelling with qubit registers explicitly correlated via a (fixed)
entangling layer. In this case quantum computers can offer advantage as
efficient samplers, which perform complex inverse transform sampling enabled by
the fundamental laws of quantum mechanics. On a technical side the advances are
multiple, as we introduce the phase feature map, analyze its properties, and
develop frequency-taming techniques that include qubit-wise training and
feature map sparsification.
Related papers
- Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties?
We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d.
We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
arXiv Detail & Related papers (2024-08-22T08:21:28Z) - On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution.
In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
arXiv Detail & Related papers (2024-05-18T15:59:41Z) - Quantum Chebyshev Transform: Mapping, Embedding, Learning and Sampling
Distributions [18.124351208075062]
We show how to encode data into quantum states with amplitudes growing exponentially in the system size.
We propose an embedding circuit for generating the orthonormal Chebyshev basis of exponential capacity.
This enables automatic model differentiation, and opens a route to solving differential equations.
arXiv Detail & Related papers (2023-06-29T15:19:32Z) - TeD-Q: a tensor network enhanced distributed hybrid quantum machine
learning framework [59.07246314484875]
TeD-Q is an open-source software framework for quantum machine learning.
It seamlessly integrates classical machine learning libraries with quantum simulators.
It provides a graphical mode in which the quantum circuit and the training progress can be visualized in real-time.
arXiv Detail & Related papers (2023-01-13T09:35:05Z) - Importance sampling for stochastic quantum simulations [68.8204255655161]
We introduce the qDrift protocol, which builds random product formulas by sampling from the Hamiltonian according to the coefficients.
We show that the simulation cost can be reduced while achieving the same accuracy, by considering the individual simulation cost during the sampling stage.
Results are confirmed by numerical simulations performed on a lattice nuclear effective field theory.
arXiv Detail & Related papers (2022-12-12T15:06:32Z) - Implementation and Learning of Quantum Hidden Markov Models [0.0]
We propose a unitary parameterization and an efficient learning algorithm for Quantum Hidden Markov Models (QHMMs)
By leveraging the richer dynamics of quantum channels, we demonstrate the greater efficiency of quantum generators compared to classical ones.
We show that any QHMM can be efficiently implemented and simulated using a quantum circuit with mid-circuit measurements.
arXiv Detail & Related papers (2022-12-07T17:25:02Z) - On Quantum Circuits for Discrete Graphical Models [1.0965065178451106]
We provide the first method that allows one to provably generate unbiased and independent samples from general discrete factor models.
Our method is compatible with multi-body interactions and its success probability does not depend on the number of variables.
Experiments with quantum simulation as well as actual quantum hardware show that our method can carry out sampling and parameter learning on quantum computers.
arXiv Detail & Related papers (2022-06-01T11:03:51Z) - Learnability of the output distributions of local quantum circuits [53.17490581210575]
We investigate, within two different oracle models, the learnability of quantum circuit Born machines.
We first show a negative result, that the output distributions of super-logarithmic depth Clifford circuits are not sample-efficiently learnable.
We show that in a more powerful oracle model, namely when directly given access to samples, the output distributions of local Clifford circuits are computationally efficiently PAC learnable.
arXiv Detail & Related papers (2021-10-11T18:00:20Z) - Bosonic field digitization for quantum computers [62.997667081978825]
We address the representation of lattice bosonic fields in a discretized field amplitude basis.
We develop methods to predict error scaling and present efficient qubit implementation strategies.
arXiv Detail & Related papers (2021-08-24T15:30:04Z) - Quantum Quantile Mechanics: Solving Stochastic Differential Equations
for Generating Time-Series [19.830330492689978]
We propose a quantum algorithm for sampling from a solution of differential equations (SDEs)
We represent the quantile function for an underlying probability distribution and extract samples as expectation values.
We test the method by simulating the Ornstein-Uhlenbeck process and sampling at times different from the initial point.
arXiv Detail & Related papers (2021-08-06T16:14:24Z) - Learnability and Complexity of Quantum Samples [26.425493366198207]
Given a quantum circuit, a quantum computer can sample the output distribution exponentially faster in the number of bits than classical computers.
Can we learn the underlying quantum distribution using models with training parameters that scale in n under a fixed training time?
We study four kinds of generative models: Deep Boltzmann machine (DBM), Generative Adrial Networks (GANs), Long Short-Term Memory (LSTM) and Autoregressive GAN, on learning quantum data set generated by deep random circuits.
arXiv Detail & Related papers (2020-10-22T18:45:25Z)
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.