About Me
I am a doctoral researcher in the field of Quantum Machine Learning (QML), affiliated with the Optimization of Machine Learning Systems Group at the University of Basel, under the supervision of Aurelien Lucchi and Jiří Černý. My research is funded by the SNSF and involves collaborative efforts with IBM Research Zürich.
In my free time, I enjoy experimenting with the musical production of various genres and arrangements. Some of my creations are archived on my YouTube channel.
Publications
- Sabri Meyer, Francesco Scala, Francesco Tacchino and Aurelien Lucchi. Trainability of Quantum Models Beyond Known Classical Simulability. arXiv preprint arXiv:2507.06344, 2025.
Research
My research focuses on the Mathematical Analysis of Variational Quantum Algorithms (VQAs), which are optimized by tuning Parameterized Quantum Circuits (PQCs) with classical algorithms. I emphasize understanding the optimization landscape of quantum expectation values in PQCs and investigating the trade-offs between trainability and classical simulability.
A major theoretical challenge in this field is the Barren Plateau Problem, which causes gradients to vanish exponentially in the model size, making it very difficult to find a good solution. While mitigation techniques can alleviate this, they consistently appear to cause the quantum model becoming classically simulable, thereby ruling out Quantum Advantage.
This led to the currently debated conjecture proposed by Cerezo et al.: Does the provable absence of barren plateaus necessarily imply classical simulability? As a mathematician, I am deeply intrigued by this theoretical challenge and the complex algebraic structures that allow for Classical Simulation strategies. My goal is to contribute to proving or disproving this fundamental conjecture.
I generally find the potential of Quantum Machine Learning (QML) fascinating, and I appreciate the opportunity to apply abstract mathematics from my graduate studies to underlying interdisciplinary problems of this field.
Conferences & Workshops
QTML 2025: 9th International Conference on Quantum Techniques in Machine Learning. Marina Bay Sands & National University of Singapore (NUS), Singapore.
LMS Research School 2025: Quantum Machine Learning and Hamiltonian Simulation. Sabhal Mor Ostaig (Gaelic College), Scotland.
QTML 2024: 8th International Conference on Quantum Techniques in Machine Learning. University of Melbourne, Australia.
Teaching
Fall Semester 2025: Teacher Assistant in Mathematics of Data Science
- Introduction to probability theory and mathematical statistics
- Random matrix theory, concentration inequalities, functional calculus and high-dimensional analysis
- Marchenko–Pastur law, neural networks, distance distributions, and stochastic processes
Fall Semester 2023: Teacher Assistant in Mathematics of Data Science
- Introduction to probability theory and mathematical statistics
- Random matrix theory, concentration inequalities, and dimensionality reduction
- Graph theory, spectral clustering, and diffusion maps
Curriculum Vitae
2023 - Present: PhD in Quantum Machine Learning, University of Basel
- Electives in Algebraic Geometry
2021 - 2023: Master of Science in Mathematics, University of Basel
- Specialized in Algebraic Number Theory, Analysis of Partial Differential Equations and Stochastic Analysis
- Master Thesis on the Hessian Eigenspectrum of Nonlinear Neural Networks
- Electives in Theoretical Quantum Mechanics
2018 - 2021: Bachelor of Science in Mathematics, University of Basel
- Electives in Physics & Computer Science