Peter E. Holderrieth

PhD student at MIT

gfalls.jpeg

MIT CSAIL, 32 Vassar St

Cambridge, MA 02139, US

I am a 2nd-year PhD student at CSAIL at MIT working with Tommi Jaakkola. I work on machine learning algorithms, in particular generative modeling, as well connections to mathematics and science (“AI for science”). During my PhD, I also interned at MetaAI working with Yaron Lipman and Ricky Chen.

Before MIT, I earned an MSc in Statistics and an MSc in Neuroscience at the University of Oxford supported by a Rhodes Scholarship where I worked with Yee Whye Teh on geometric deep learning and with Stephen Smith on transfer learning for neuroimaging. I graduated with a BSc in Mathematics from the wonderful University of Bonn where I worked with Andreas Eberle on stochastic differential equations.

In the past, I also worked or interned at several Biotech/AI startups (Cellarity, Genomics plc), at BCG, at the Max Planck Institute, and at the German Parliament. Besides my work, I have a passion for writing music, swimming, and hiking.

selected publications

  1. leaps-teaser.png
    LEAPS: A discrete neural sampler via locally equivariant networks
    Peter Holderrieth*, Michael S Albergo*, and Tommi Jaakkola
    arXiv preprint arXiv:2502.10843, 2025
  2. gm-teaser.png
    Generator Matching: Generative modeling with arbitrary Markov processes
    Peter Holderrieth, Marton Havasi, Jason Yim, and 6 more authors
    ICLR 2025, Oral (top 1% of submissions), 2024

latest posts