Quantum Learning Theory
August 21-25, 2023
We are entering the exciting era where quantum computers are no longer a theoretical construction but a physical reality. However, now and in the near future, the available quantum computing hardware is noisy. Therefore, it is crucial to use quantum resources efficiently: the difference between noise and signal may lie in just a slightly smarter use of the number of available qubits or circuit depth. A convenient theoretical perspective is provided by quantum learning theory, which poses the following question: given access to a quantum state, how can we learn properties of the state as efficiently as possible?
Apart from using near-term noisy devices for useful applications, quantum learning theory is also fundamental to understand the power of quantum computation for future fault-tolerant devices. How does quantum learning compare to classical learning theory? Can we find speed-ups over classical algorithms when trying to learn either classical or quantum systems?
Target audience
This master class will be of interest for all students and early career researchers interested in properties, applications and future research directions involving quantum learning theory.
