Elies Gil Fuster

About

I’m a last-year PhD student working on Quantum Machine Learning (QML) in Jens Eisert's group in Berlin, I also have half-a-leg in Vedran Dunjko's group in Leiden. The main goal of my PhD has been to contribute to the mathematical foundations of QML theory. I have made contributions to the design of new QML models and the study of their generalization. I have also worked on dequantization, showing how many QML models can fail to realize quantum advantage in learning, and proposing robust designs which cannot be dequantized. Looking forward, I want to deepen my knowledge of quantum algorithms and complexity theory.

If you’d like to get in touch, please drop me an email or find me on Bluesky, as @eliesgf.

You can find more information in my CV. A complete list of publications can be found in my Google Scholar profile.

Publications

Peer-reviewed

Potential and limitations of random Fourier features for dequantizing quantum machine learning (2025).
Sweke R., Recio E., Jerbi S., Gil-Fuster E., Fuller B., Eisert J., and Meyer J. J.
Quantum 9, 1640.
On the relation between trainability and dequantization of variational quantum learning models (2025).
Gil-Fuster E., Gyurik C., Pérez-Salinas A., and Dunjko V.
ICLR 2025, arXiv:2406.07072.
On the expressivity of embedding quantum kernels (2024).
Gil-Fuster E., Eisert J., and Dunjko V.
Mach. Learn.: Sci. Technol. 5 025003.
Understanding quantum machine learning also requires rethinking generalization (2024).
Gil-Fuster E., Eisert J., and Bravo-Prieto C.
Nat. Comms. 15, 2277.
Exploiting symmetry in variational quantum machine learning (2023)
Meyer J.J., Mularski M., Gil-Fuster E., Mele A.A., Arzani F., Wilms A., and Eisert J.
PRX Quantum 4, 010328.
Training Quantum Embedding Kernels on Near-Term Quantum Computers (2022)
Hubregtsen T., Wierichs D., Gil-Fuster E., Derks P.J.H.S., Faehrmann P.K., and Meyer J. J.
PRA 106, 042431, arXiv:2105.02276.
Encoding-dependent generalization bounds for parametrized quantum circuits (2021).
Caro M.C., Gil-Fuster E., Meyer J.J., Eisert J., and Sweke R.
Quantum 5, 582.
Data re-uploading for a universal quantum classifier (2020).
Pérez-Salinas A., Cervera-Lierta A., Gil-Fuster E., and Latorre J. I.
Quantum 4, 226.

Pre-prints

Prospects for quantum advantage in machine learning from the representability of functions (2025).
Masot-Llima S., Gil-Fuster E., Bravo-Prieto C., Eisert J., Guaita T.
arXiv:2512.15661.
Quantum computing and artificial intelligence: status and perspectives (2025).
Acampora G., …, Gil-Fuster E., …,
arXiv:2505.23860.
Kernel-based dequantization of variational QML without Random Fourier Features (2025).
Sweke R., Shin S., Gil-Fuster E.
arXiv:2503.23931.
Double descent in quantum machine learning (2025).
Kempkes M., Ijaz A., Gil-Fuster E., Bravo-Prieto C., Spiegelberg J. van Nieuwenburg E., Dunjko V.
arXiv:2501.10077.
Opportunities and limitations of explaining quantum machine learning (2024).
Gil-Fuster E., Naujoks J.R., Montavon G., Wiegand T., Samek W., Eisert J.
arXiv:2412.14753.
Concept learning of parameterized quantum models from limited measurements (2024).
Gan B.Y., Huang P.-W., Gil-Fuster E., Rebentrost P.
arXiv:2408.05116.

Conferences & talks

Conferences

2024.XI | Talk: Kernel-based dequantization of variational QML | QTML2024.
2024.XI | Talk: On the expressivity of embedding quantum kernels | QTML2024.
2024.IX | Poster: On the relation between trainability and dequantization of variational quantum learning models | SeeQA 2024.
2024.IV | Talk: Understanding quantum machine learning also requires rethinking generalization | QCTiP2024.
2024.IV | Poster: On the expressivity of embedding quantum kernels | QCTiP2024.
2024.III | Talk: On the expressivity of embedding quantum kernels | DPG March meeting 2024.
2024.III | Talk: Understanding quantum machine learning also requires rethinking generalization | DPG March meeting 2024.
2024.I | Poster: Understanding quantum machine learning also requires rethinking generalization | QIP2024.
2023.XI | Talk: Understanding quantum machine learning also requires rethinking generalization | QTML2023.
2022.XI | Poster: Non-Embedding Quantum Kernels, do they exist? | QTML2022.
2021.XI | Talk: Encoding-dependent generalization bounds for parametrized quantum circuits | QTML2021.
2020.III | Poster: Data re-uploading for a universal quantum classifier | QCTIP2020.

Seminars and workshops

2025.VII | Seminar: On the relation between trainability and dequantization of variational quantum learning models | Condensed Matter Seminar at ICTP Trieste.
2025.V | Seminar: Kernel-based dequantization of variational QML without Random Fourier Features | Juan Carrasquilla's group meeting at ETH Z"urich.
2025.IV | Seminar: Kernel-based dequantization of variational QML without Random Fourier Features | QCS Meeting at IBM Research Europe.
2025.III | Tutorial: The quantum kernel saga | Tutorial Seminar at AG Eisert, FU Berlin.
2025.II | Seminar: On the relation between trainability and dequantization of variational quantum learning models | Quantum Pod seminar at UC Berkeley.
2025.II | Seminar: On the relation between trainability and dequantization of variational quantum learning models | IQIM seminar at Caltech.
2024.X | Talk: Machine Learning on Quantum Computers: how it started vs. how it’s going | BMW QC Community.
2024.X | Seminar: On the relation between trainability and dequantization of variational quantum learning models | QMAI team seminar at TU Delft.
2024.X | Workshop talk: On the expressivity of embedding quantum kernels | Défi Eqip workshop at Université Paris-Saclay.
2024.VIII | Poster: On the relation between trainability and dequantization of variational quantum learning models | QMATH Summer School on quantum simulation.
2024.VII | Seminar: On the relation between trainability and dequantization of variational quantum learning models | Kappen group seminar.
2024.VII | Seminar: On the relation between trainability and dequantization of variational quantum learning models | QTI Journal Club at CERN.
2024.IV | Seminar: On the expressivity of embedding quantum kernels | GIQ Seminar at UAB.
2024.II | Seminar: On the expressivity of embedding quantum kernels | IBM Q UK seminar.
2024.I | Seminar: On the expressivity of embedding quantum kernels | QAISG QML seminar.
2023.XII | Seminar: On the expressivity of embedding quantum kernels | aQa seminar at Leiden University.
2023.XI | Seminar: On the expressivity of embedding quantum kernels | QIC seminar at EPFL.
2023.XI | Seminar: Understanding quantum machine learning also requires rethinking generalization | Einstein Research Unit update meeting.
2023.X | Seminar: Understanding quantum machine learning also requires rethinking generalization | Google Quantum AI QML meeting.
2023.X | Seminar: Understanding quantum machine learning also requires rethinking generalization | QAISG QML seminar.
2023.IX | Seminar: Understanding quantum machine learning also requires rethinking generalization | QUANTIC group seminar.
2023.VI | Participated: Quantum Information workshop | Centro de ciencias de Benasque Pedro Pascual.
2023.IV | Workshop talk: Exploiting symmetry in variational quantum machine learning | Machine Learning and (Quantum) Physics workshop.
2023.I | Seminar: Exploiting symmetry in variational quantum machine learning | QUANTIC group seminar.
2021.XII | Workshop talk: Training quantum embedding kernels on near-term quantum computers | “Theory of Quantum Machine Learning”.
2021.XI | Seminar: Encoding-dependent generalization bounds for parametrized quantum circuits | Tomamichel Group Seminar.
2021.IX | Workshop poster: Generalization bounds in the quantum realm | EDS2021.
2020.V | Participated: Hands-on Quantum Computing Summer School | Centro de ciencias de Benasque Pedro Pascual.

Contact

Elies Gil-Fuster
Dahlem Center for Complex Quantum Systems
Freie Universität Berlin
Arnimallee 14
14195 Berlin
Germany

Elies Gil-Fuster, 2026

Hi, I’m Elies Gil-Fuster