"My goal is to design effective quantum machine learning algorithms for Noisy Intermediate-Scale Quantum (NISQ) devices. This task poses challenging questions in quantum complexity and statistical learning theory, as we wish to prove a quantum advantage both in terms of time and sample complexity.

Moreover, I am interested in secure delegation protocol for machine learning algorithms. NISQ devices will be remotely available to clients, thus privacy-preserving delegation protocols are crucial when the input contains personal (e.g. biometric) information.

I am interested as well in classical machine learning problems, such  as clustering and generative modelling."

Research unit: UMR 7606 / Laboratoire d’informatique de Paris 6 / LIP6
Director, Elham Kashefi (QI) & Co-superviseur, Vincent Cohen Addad (RO)

Keywords:
Quantum machine learning, quantum advantage, privacy-preserving machine learning, generative models, statistical learning theory