Our Lunch Seminar series continues on Monday, March 7! We will host Giuseppe Sergioli (University of Cagliari) who will give a talk on Quantum Information and Machine Learning. From foundations to real applications See below for more information and the abstract:
Abstract. This talk is about the connection between quantum in-
formation theory and machine learning. In particular, we show how quantum state discrimination can represent a useful tool to address the standard classification problem in machine learning. We show how the optimal quantum measurement theory developed in the context of quantum information theory and quantum communication can inspire a new binary classification algorithm that can achieve higher inference accuracy for various datasets. Here we also propose a model for arbitrary multiclass classification inspired by quantum state discrimination, which is enabled by encoding the data in the space of linear operators on a Hilbert space. We also show a full comparison between quantum inspired and other standard classifiers over artificial and real datasets.