Machine learning provides new and unprecedented insights into properties of complex quantum systems. At the same time, notions of quantum assisted machine learning may improve notions of machine learning and provide applications of near-term quantum computing. We aim at exploring such new applications and think of a rigorous theory of learning in the quantum realm, establishing what we like to call "proof pockets".

Selected group publications

• Expressive power of tensor-network factorizations for probabilistic modeling, with applications from hidden Markov models to quantum machine learning
  Advances in Neural Information Processing Systems 32, Proceedings of the NeurIPS 2019 Conference
• Stochastic gradient descent for hybrid quantum-classical optimization
  Quantum 4, 314 (2020)
• On the quantum versus classical learnability of discrete distributions
  arXiv:2007.14451, Quantum in press (2021)
• Reinforcement learning decoders for fault-tolerant quantum computation
  Machine Learning in Science Technology 2, 025005 (2021)
• Tensor network approaches for learning non-linear dynamical laws
  arXiv:2002.12388