Quantum Stochastics and Quantum Learning

Recent advancements in quantum technology, such as quantum computing, communication and metrology have created renewed interest in the probabilistic and statistical challenges posed by quantum information theory. While the fundamental principles of detecting and processing statistical signals remain the same, the statistical inference and information-theoretic bounds in quantum models deviate from their classical counterparts due to the unique nature of quantum probability. As a result, findings often differ in non-trivial ways.

This seminar aims to explore stochastic problems arising from quantum systems in a unified way, beginning with the foundational principles of quantum probability. Topics will include , but are not limited to, quantum statistical estimation and hypothesis testing, quantum limit theorems and quantum information geometry.

The lectures on quantum learning theory (learning, certification, and tomography) and tensor norms are based on lecture notes of John Wright and lecture notes of Ion Nechita respectively.

Lecture Slides