Currently Third year Postodoctoral Researcher at The University of Edinburgh, Scotland, leading the Quantum Machine Learning team under Elham's Kashefi supervision. Our research goals concerns the provability of quantum advantage for near term quantum machine learning proposals such as variational quantum circuits and hamming weight preserving quantum circuits.
Previously, I was a Ph.D. student at the University of Paris, under the direction of Iordanis KERENIDIS from the IRIF Algorithm and Complexity team. I worked on developing new algorithms for long and short term quantum computers, in particular quantum algorithms for machine learning. My main research consists in identifying classical machine learning algorithms that could potentially be adapted to the quantum computing framework with provable speedup.
We develop fundamental quantum circuits to process data, defining routines for linear algebra, graph, analytic computations. In my recent works I have been focused on developing:
These routines are at the core of new quantum algorithms for unsupervised machine learning such as k-means clustering, Gaussian mixture models, spectral clustering, as well as fully connected and convolutional neural networks, and many others. Link to PhD Thesis "Quantum Algorithms for Unsupervised Machine Learning and Neural Networks" (2021)
Topics : Quantum algorithms for ML / Training of variational quantum circuits for ML :
email : jonas ldmn [@] gmail .com