Generating high-quality data (e.g., images or video) is one of the most exciting and challenging frontiers in unsupervised machine learning. Utilizing quantum computers in such tasks to potentially enhance conventional machine learning algorithms has emerged as a promising application, but poses big challenges due to the limited number of qubits and the level of gate noise in available devices.
Researchers at Zapata Computing and IonQ have provided the first practical and experimental implementation of a quantum-classical generative algorithm capable of generating high-resolution images of handwritten digits with state-of-the-art gate-based quantum computers.
In their quantum-enhanced machine learning model, they have implemented a quantum-circuit based generative model to sample the prior distribution of a Generative Adversarial Network (GAN). They introduced a multi-basis technique which leverages the unique possibility of measuring quantum states in different bases, hence enhancing the expressibility of the prior distribution to be learned.
They demonstrated a full training of this hybrid algorithm on an ion-trap device based on 171Yb+ ion qubits to generate high-quality images and quantitatively outperform comparable classical GANs trained on the popular MNIST dataset for handwritten digits.