Publications

[19]: "A provable quantum advantage for approximate optimization via decoded quantum interferometry",

Maximilian J. Kramer, EGF, Benjamin D. M. Jones, Jens Eisert, Franz J. Schreiber.

[arxiv 2026].

[18]: "Approximate sampling from decoded quantum interferometry via Markov chain Monte Carlo methods",

EGF, Matan Ninio, Lennart Bittel, Yishai Shimoni, Jens Eisert, Stefan Woerner, Almudena Carrera Vázquez.

[arxiv 2026].

[17]: "Cautious optimism for deep parameterized quantum circuits",

Marie Kempkes, EGF, Carlos Bravo-Prieto, Aroosa Ijaz, Alissa Wilms, Jens Eisert, Evert van Nieuwenburg, Vedran Dunjko.

[arxiv 2026].

⭐ [16]: "Optimal algorithmic complexity of inference in quantum kernel methods",

EGF, Seongwook Shin, Sofiene Jerbi, Jens Eisert, Maximilian J. Kramer.

[arxiv 2026].

Accepted in NeurIPS 2026.

[15]: "A PAC-Bayesian approach to generalization for quantum models",

Pablo Rodriguez-Grasa, Matthias C. Caro, Jens Eisert, EGF, Franz J. Schreiber, Carlos Bravo-Prieto.

[arxiv 2026].

Talk @ QTML 2025.

[14]: "Prospects for quantum advantage in machine learning from the representability of functions",

Sergi Masot-Llima*, EGF*, Carlos Bravo-Prieto, Jens Eisert, Tommaso Guaita.

[arxiv 2025].

Posters @ QTML 2025, QCTiP 2026.

[13]: "Quantum computing and artificial intelligence: status and perspectives",

Giovanni Acampora, ..., EGF, ...

[arxiv 2025].

[12]: "Kernel-based dequantization of variational QML without Random Fourier Features",

Ryan Sweke, Seongwook Shin, EGF.

[arxiv 2025].

Talk @ QTML 2025.

[11]: "Opportunities and limitations of explaining quantum machine learning",

EGF, Jonas R. Naujoks, Grégoire Montavon, Thomas Wiegand, Wojciech Samek, Jens Eisert.

[arxiv 2024].

Talk @ QTML 2024.

[10]: "Concept learning of parameterized quantum models from limited measurements",

Beng Yee Gan, Po-Wei Huang, EGF, Patrick Rebentrost.

[arxiv 2024].

[9]: "Double descent in Quantum Kernel Methods",

Marie Kempkes, Aroosa Ijaz, EGF, Carlos Bravo-Prieto, Jakob Spiegelberg, Evert van Nieuwenburg, Vedran Dunjko.

[PRX Quantum], [arxiv 2025].

[8]: "Potential and limitations of random Fourier features for dequantizing quantum machine learning",

Ryan Sweke, Erik Recio-Armengol, Sofiene Jerbi, EGF, Bryce Fuller, Jens Eisert, Johannes Jakob Meyer.

[Quantum], [arxiv 2023].

Talk @ QTML 2025.

⭐ [7]: "On the relation between trainability and dequantization of variational quantum learning models",

EGF, Casper Gyurik, Adrián Pérez-Salinas, Vedran Dunjko.

[ICLR], [arxiv 2024].

Talk @ QTML 2024.

[6]: "On the expressivity of embedding quantum kernels",

EGF, Jens Eisert, Vedran Dunjko.

[MLST], [arxiv 2023].

Talk @ QTML 2024, Poster @ QTML 2022.

⭐ [5]: "Understanding quantum machine learning also requires rethinking generalization",

EGF, Jens Eisert, Carlos Bravo-Prieto.

[Nature Communications], [arxiv 2023].

Talks @ QTML 2023, QCTiP 2024, Poster @ QIP 2024.

[4]: "Exploiting symmetry in variational quantum machine learning",

Johannes Jakob Meyer, Marian Mularski, EGF, Antonio Anna Mele, Francesco Arzani, Alissa Wilms, Jens Eisert

[PRX Quantum], [arxiv 2022].

Talk @ QTML 2022.

[3]: "Training Quantum Embedding Kernels on Near-Term Quantum Computers",

Thomas Hubregtsen, David Wierichs, EGF, Peter-Jan H. S. Derks, Paul K. Faehrmann, Johannes Jakob Meyer.

[PRA], [arxiv 2021].

First prize and sponsor prize @ QHACK 2021.

[2]: "Encoding-dependent generalization bounds for parametrized quantum circuits",

Matthias C. Caro, EGF, Johannes J. Meyer, Jens Eisert, Ryan Sweke.

[Quantum], [arxiv 2021].

Talk @ QTML 2021.

⭐ [1]: "Data re-uploading for a universal quantum classifier",

Adrián Pérez-Salinas, Alba Cervera-Lierta, EGF, José Ignacio Latorre.

[Quantum], [arxiv 2019].

Talk @ QTML 2020, Poster @ QCTiP 2020.