Quantifying the complexity of learning quantum features

Giorno 20 ottobre 2025, con inizio alle ore 16:00, presso l'Aula T del DFA, il Prof. Leonardo Banchi (Università di Firenze) terrà un seminario dal titolo Quantifying the complexity of learning quantum features.

Modera il Dott. Riccardo Cantone (Dottorando in Fisica, 41° ciclo).

Il seminario appartiene al ciclo degli Highlights in Frontier Physics, nell'ambito delle attività del Dottorato di ricerca in Fisica.

Tutte le persone interessate sono invitate a partecipare.

Il Professor Banchi terrà altresì una lezione su "Introduction to Quantum Machine Learning" martedì 21 ottobre 2025 dalle ore 15:00 alle ore 17:00 in Aula A.

Abstract. The ability to extract general laws from a few known examples depends on the complexity of the problem and on the amount of training data. For learning tasks with "quantum data", e.g. quantum states and channels, the learner's performance is further challenged by the destructive nature of quantum measurements.  Using tools from statistical learning theory we will study which of these tasks are easy in the many-particle setting. For instance, we will show that learning to classify entanglement is challenging, as the problem needs many measurements. On the other hand, learning an observable (like an order parameter) able to identify quantum phases of matter is easy, as, in some cases, only a polynomial number of "simple" measurements is required. Finally, we discuss a possible quantum advantage in learning classical temporal stochastic processes, where quantum models can reach high accuracy with less training data.