Protocols for classically training quantum generative models on probability distributions

by   Sachin Kasture, et al.

Quantum Generative Modelling (QGM) relies on preparing quantum states and generating samples from these states as hidden - or known - probability distributions. As distributions from some classes of quantum states (circuits) are inherently hard to sample classically, QGM represents an excellent testbed for quantum supremacy experiments. Furthermore, generative tasks are increasingly relevant for industrial machine learning applications, and thus QGM is a strong candidate for demonstrating a practical quantum advantage. However, this requires that quantum circuits are trained to represent industrially relevant distributions, and the corresponding training stage has an extensive training cost for current quantum hardware in practice. In this work, we propose protocols for classical training of QGMs based on circuits of the specific type that admit an efficient gradient computation, while remaining hard to sample. In particular, we consider Instantaneous Quantum Polynomial (IQP) circuits and their extensions. Showing their classical simulability in terms of the time complexity, sparsity and anti-concentration properties, we develop a classically tractable way of simulating their output probability distributions, allowing classical training to a target probability distribution. The corresponding quantum sampling from IQPs can be performed efficiently, unlike when using classical sampling. We numerically demonstrate the end-to-end training of IQP circuits using probability distributions for up to 30 qubits on a regular desktop computer. When applied to industrially relevant distributions this combination of classical training with quantum sampling represents an avenue for reaching advantage in the NISQ era.


Classically Simulating Quantum Circuits with Local Depolarizing Noise

We study the effect of noise on the classical simulatability of quantum ...

Learning hard quantum distributions with variational autoencoders

Studying general quantum many-body systems is one of the major challenge...

Enhancing Generative Models via Quantum Correlations

Generative modeling using samples drawn from the probability distributio...

Expressive probabilistic sampling in recurrent neural networks

In sampling-based Bayesian models of brain function, neural activities a...

Fermion Sampling Made More Efficient

Fermion sampling is to generate probability distribution of a many-body ...

Learnability and Complexity of Quantum Samples

Given a quantum circuit, a quantum computer can sample the output distri...

Testing Probabilistic Circuits

Probabilistic circuits (PCs) are a powerful modeling framework for repre...

Please sign up or login with your details

Forgot password? Click here to reset