Entanglement, that is, quantum correlations that do not have a classical counterpart, is a resource for quantum information processing. I provide an overview on the entanglement theory by focusing on the structure of entangled states. I also discuss the experimental verification of entangled states given assumptions made on sources and measurements.
Machine Learning is, in most cases, powerful but a black-box application. In this talk, we will tackle this very problem from a quantum mechanics point of view, arguing that an optimisation problem, such as classification or anomaly detection, can be studied by “rephrasing" the problem as a quantum many-body system or a mixed state. Such an approach allows us to employ the entire arsenal of...
Nonparametric methods, such as nearest neighbor and kernel methods, can offer simple and parallelizable algorithms without the need for manual structure tunning. However, these methods may suffer from severe performance degradation due to biases from the high-dimensionality of data. I will introduce recently derived equations for understanding and addressing the high-dimensional bias and...
Neural Networks (NN), the backbones of Deep Learning, define field theories through output ensembles at initialization. Certain limits of NN architecture give rise to free field theories via Central Limit Theorem (CLT), whereas other regimes give rise to weakly coupled, and non-perturbative field theories, via small, and large deviations from CLT, respectively. I will present a systematic...
