Kaggle Silver Medal - NeuroGolf 2026
Ranked 40th (top 1.4%) in an AI-agent and ONNX optimization challenge. Built an iterative agent workflow for exact verification, parameter reduction and memory-constrained model design.
Code CompetitionHello! I am a PhD candidate in Mathematics at Imperial College London, supervised by Professor Dan Crisan. My research concerns stochastic analysis and numerical methods for fluid-dynamics PDEs and SPDEs, with a particular focus on vortex methods and interacting particle systems.
Working with particle systems, McKean–Vlasov equations and nonlinear PDEs led me to explore modern machine-learning architectures from a more mathematical perspective. I am increasingly interested in understanding the internal behaviour and representations of large models.
Alongside my PhD, I work on applied machine learning projects at Stripe Partners.
I enjoy working where theory informs engineering, and where experiments help refine theoretical understanding.
Ranked 40th (top 1.4%) in an AI-agent and ONNX optimization challenge. Built an iterative agent workflow for exact verification, parameter reduction and memory-constrained model design.
Code CompetitionImplemented causal multi-head attention, residual blocks, normalization and a language-model head in PyTorch; developing the TinyStories training and evaluation pipeline.
Ongoing
Iman Munire Bilal, Yingcan Carol Wang, Ajan Raj, Filippo Giovagnini, Pranav Tewari, Yuwei Zhang, Mei-Chen Zoe Liou, Qamar Zaman
Preprint, 2026
Filippo Giovagnini, Sotirios Kotitsas, Marco Romito
Preprint, 2026
Lucio Galeati, Filippo Giovagnini, Massimo Sorella
Preprint, 2026
Filippo Giovagnini, Dan Crisan
Preprint, 2025
Filippo Giovagnini, Dan Crisan
Preprint, 2024
PhD in Stochastic Analysis, supervised by Professor Dan Crisan
2023 - Present
Exchange programme in Mathematics
2023
Master's and Bachelor's degrees in Mathematics
2018 - 2023
2025/26
Current course notes and revision properties.
2024/25 archive
A notebook illustrating Brownian motion for students working through the course material.
Notebook