publications

A few research work I have published over the years. More to come!

2025

  1. LEAPS: A discrete neural sampler via locally equivariant networks
    Peter Holderrieth*, Michael S Albergo*, and Tommi Jaakkola
    ICML 2025
    Best Paper Award at Frontiers in Probabilistic Inference workshop at ICLR 2025

2024

  1. Generator Matching: Generative modeling with arbitrary Markov processes
    Peter Holderrieth, Marton Havasi, Jason Yim, and 6 more authors
    ICLR 2025
    ICLR Oral (top 1% of submissions)
  2. Flow Matching Guide and Code
    Yaron Lipman, Marton Havasi, Peter Holderrieth, and 7 more authors
    MetaAI research
  3. Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective
    Neta Shaul, Itai Gat, Marton Havasi, and 6 more authors
    ICLR 2025
    ICLR Oral (top 1% of submissions)
  4. Hamiltonian Score Matching and Generative Flows
    Peter Holderrieth, Yilun Xu, and Tommi Jaakkola
    NeurIPS 2024

2022

  1. Transfer Learning for Neuroimaging via Re-use of Deep Neural Network Features
    Peter Holderrieth, Stephen Smith, and Han Peng
    medRxiv

2021

  1. Equivariant learning of stochastic fields: Gaussian processes and steerable conditional neural processes
    Peter Holderrieth, Michael J Hutchinson, and Yee Whye Teh
    ICML 2021

2020

  1. Cores for piecewise-deterministic Markov processes used in Markov chain Monte Carlo
    Peter Holderrieth
    Electronic Communications in Probability, volume 26