Josep Lumbreras

Josep Lumbreras

A researcher learning in quantum environments

About

I am Josep Lumbreras, a Ph.D. student at Centre for Quantum Technologies (National University of Singapore) under the supervision of Prof. Marco Tomamichel. Previously I completed a double major in physics and mathematics and a master’s in particle physics and gravitation at University of Barcelona.

Research interests

My main line of research lies in proving rigorous theoretical results at the intersection of Machine Learning and Quantum Information. Specifically I am interested in the application of multi-armed bandit theory to quantum learning tasks, as well as contributions to the classical problem of stochastic bandits. This includes:

  • Identifying which quantum tasks the exploration-exploitation dilemma is relevant.
  • Designing new algorithms and proving information theoretical lower bounds where the underlying structure of the problem is quantum.

Additionally, I work on the generalization of (Partially Observable) Hidden Markov Models into quantum and general probabilistic theories.

Publications

  1. Learning pure quantum states (almost) without regret
    J. Lumbreras, M. Terekhov, M. Tomamichel.
    [AQIS24 (long talk)][arXiv (2024)]

  2. Linear bandits with polylogarithmic minimax regret
    J. Lumbreras, M. Tomamichel.
    [COLT (2024)][arXiv (2024)]

  3. Learning finitely correlated states: stability of the spectral reconstruction
    M. Fanizza, N. Galke, J. Lumbreras, C. Rouzé, A. Winter.
    [Beyond IID 2024][arXiv (2024)]

  4. Quantum Theory in Finite Dimension Cannot Explain Every General Process with Finite Memory
    M. Fanizza†, J. Lumbreras† (co-first author), A. Winter.
    [ Communications in Mathematical Physics][TQC 23][Beyond IID 2022][arXiv (2023)]

  5. Quantum contextual bandits and recommender systems for quantum data
    S. Brahmachari†, J. Lumbreras† (co-first author), M. Tomamichel.
    [Quantum Machine Intelligence][arXiv (2023)]

  6. Multi-armed quantum bandits: Exploration versus exploitation when learning properties of quantum states
    J. Lumbreras, E. Haapasalo, M. Tomamichel.
    [Quantum][AQIS 21 (long talk)][Beyond IID 2021][QTML 21][arXiv (2022)]

  7. Scaling of variational quantum circuit depth for condensed matter systems
    C. Bravo†, J. Lumbreras† (co-first author), L. Tagliacozzo, J. I. Latorre.
    [Quantum][arXiv (2020)]