Nicolò Ruggeri
Nicolò Ruggeri
PhD Student in Machine Learning and Network Science

Hey there!

You appear to have landed on my website.
My name is Nicolò Ruggeri, I am a Machine Learning Scientist with an interest for generative modelling and applications in biology.

Previously, I obtained a Ph.D. within the Max Planck ETH Center for Learning Systems, in between MPI for Intelligent Systems (Tübingen) and ETH (Zürich).
There, I was co-supervised by Caterina De Bacco and Fanny Yang.

My research revolves around probabilistic methods in machine learning and their applications. Lately, I have also been tackling complex problems in biology with a variety of these tools.

Some keywords that might or might not make sense include:

  • Generative modelling
    • Diffusion methods & affine
    • Protein design
    • Foundational models for omics
  • Variational inference
    • Ranking on networks
    • Variational autoencoders
    • Interpretability and disentanglement
  • Graphs
    • Modelling of network-type data
    • Community detection
    • Message passing, EM-inference and general probabilistic inference
Broadly speaking, I am interested in both theory and applications, as well as any topic related to the above.
I also have a keen interest in clean and efficient code.
So feel free to get in touch!

News

  • 23/04/2024 - I joined DeepLife, where I'll be developing foundation models for target identification using multi-modal omics data.

  • 23/04/2024 - Our paper
      "Message-passing on hypergraphs: detectability, phase transitions and higher-order information"
      has been accepted in JSTAT!

  • 23/04/2024 - I joined Epsilico, where I'll be developing generative models for protein design.

  • 12/07/2023 - Our paper
      "Community detection in large hypergraphs"
      has been accepted in Science Advances!

  • 15/05/2022 - Our paper
      "Fast rates for noisy interpolation require rethinking the effects of inductive bias"
      has been accepted at ICML 2022!

  • 01/04/2022 - We have released our new work:
      "Provable concept learning for interpretable predictions using variational inference" (ArXiv)

  • 26/11/2021 - I was listed among the AISTSAT 2021 outstanding reviewers!