Ouns El Harzli
Interests
My interest is in the broad field of artificial intelligence and machine learning theory.
In my research, I explore a wide range of mathematical formalisms and tools to try and answer two intertwined (and unsolved) questions in deep learning theory: 1) why do deep neural networks generalise well ? and 2) how to make their predictions explainable ?
Mathematical frameworks that I have used in my research/of interest: formal logic, computational complexity theory, algorithmic information theory, statistical physics, random matrix theory, probability theory, Bayesian statistics, statistical learning theory, continuous optimisation, discrete optimisation.
Deep learning research topics that I have covered in my research/of interest: explainability, generalisation, emergent phenomena (e.g. double-descent, grokking, neural collapse, low-rank bias), training dynamics (e.g. unconstrained feature models, feature learning), algorithmic stability, model compression (e.g. pruning), adversarial attacks, graph neural networks, transformers, diffusion models, large language models, mechanistic interpretability (e.g. sparse auto-encoders), neurosymbolic architectures (e.g. fibring, logic tensor networks), logical expressiveness, formal verification, Bayesian neural networks.
In terms of deep learning applications, I have worked on knowledge graphs, bioinformatics, image generation and more recently, integer programming.
Biography
I am a final-year DPhil student in Computer Science working on mathematical theories of deep learning, in particular interpretability and generalisation. My goal is to develop a principled understanding of the generalisation capabilities of neural-network-based AI systems and use the latter to design interpretability methods with formal guarantees.
Prior to this, I obtained a MSc in Mathematics from University of Oxford and a Diplôme d'Ingénieur from Ecole des Mines de Paris (a French Grande École), after attending Classe Préparatoire in Mathematics and Physics. Through various internships, I gained experience in industrial engineering, data science, applied machine learning, operations research and finance. Prior to my DPhil, I also did graduate-level research on computer vision and astrophysics.