lorenzo stigliano

i am a d.phil. candidate at the university of oxford, working at the intersection of machine learning and biomedical science. i am funded by the epsrc centre for doctoral training in healthcare data science.

before oxford, i completed a b.sc. in computer science and mathematics at the university of edinburgh, and an m.sc. in artificial intelligence and machine learning at imperial college london, where i worked in the brain and signal analysis lab on knowledge distillation for graph neural networks. i subsequently worked as a data scientist at j.p. morgan in the applied ai & ml team. a full cv can be found here.

research

my research focuses on scientifically-grounded models for multi-omics data. i incorporate domain knowledge as structured inductive biases to respect the causal and statistical relationships between genomic modalities, with a particular focus on oncology. learn more about my research a here.

selected work

• reproducible knowledge distillation for graph neural networks (2023)
  repkd: a two-stage framework that jointly trains multiple student gnns in a one-to-many teacher–student setup, improving reproducibility while achieving over 95% parameter reduction.
• introduction to inverse problems and markov chain monte carlo methods (2021)
  develops and compares metropolis–hastings and non-reversible mcmc samplers via bayesian inference, with applications to imaging inverse problems.

contact

i am always keen to collaborate with researchers working on machine learning methodology and its applications to healthcare and other high-impact domains. please feel free to get in touch if you are interested in working with me!

email  ·  github  ·  linkedin  ·  academic profile