Chiara Leadbeater's scientific contributions

Publications (2)

Preprint
Generative modelling is an important unsupervised task in machine learning. In this work, we study a hybrid quantum-classical approach to this task, based on the use of a quantum circuit Born machine. In particular, we consider training a quantum circuit Born machine using $f$-divergences. We first discuss the adversarial framework for generative m...
Article
Full-text available
Generative modelling is an important unsupervised task in machine learning. In this work, we study a hybrid quantum-classical approach to this task, based on the use of a quantum circuit born machine. In particular, we consider training a quantum circuit born machine using f-divergences. We first discuss the adversarial framework for generative mod...

Citations

... , for some distance measure D[·, ·], and getting the optimal angles θ opt = argmin θ L QCBM θ,t at fixed t. In practice, this is achieved using data samples x ∈ X data (typically, from observations) and a proxy loss, corresponding to maximum mean discrepancy (MMD) [17], Stein discrepancy (SD) [18], Kullback-Leibler divergence, as well as other types of f-divergences [42]. Once p QCBM θ,t (x) is successfully trained, one can proceed directly to sampling from the same circuit. ...