Edit Page

Tim Reichelt

• Personal Webpage
• GitHub
• Twitter

Probabilistic Programming, Probabilistic Inference

I am a PhD student at the University of Oxford lucky to be supervised by Luke Ong and Tom Rainforth as part of the AIMS Centre for Doctoral Training. I have broad interests in probabilistic machine learning, Bayesian statistics and deep learning. On a high-level, I like to build tools which help people make better data-driven decisions. More specifically, I do research in the field of probabilistic programming languages.

Publications

2023

• T. Reichelt , L. Ong , T. Rainforth , Pitfalls of Full Bayesian Inference in Universal Probabilistic Programming, in POPL Workshop on Languages for Inference (LAFI), 2023.
  

  @inproceedings{reichelt2023pitfalls,
    title = {Pitfalls of Full Bayesian Inference in Universal Probabilistic Programming},
    author = {Reichelt, Tim and Ong, Luke and Rainforth, Tom},
    year = {2023},
    booktitle = {POPL Workshop on Languages for Inference (LAFI)}
  }
  

2022

• T. Reichelt , L. Ong , T. Rainforth , Rethinking Variational Inference for Probabilistic Programs with Stochastic Support, in Advances in Neural Information Processing Systems, 2022.
  

  @inproceedings{reichelt2022rethinking,
    title = {Rethinking Variational Inference for Probabilistic Programs with Stochastic Support},
    author = {Reichelt, Tim and Ong, Luke and Rainforth, Tom},
    year = {2022},
    booktitle = {Advances in Neural Information Processing Systems}
  }
  

• T. Reichelt , A. Goliński , L. Ong , T. Rainforth , Expectation programming: Adapting probabilistic programming systems to estimate expectations efficiently, in Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, 2022.
  
  @inproceedings{reichelt2022expectation,
    title = {Expectation programming: Adapting probabilistic programming systems to estimate expectations efficiently},
    author = {Reichelt, Tim and Goli{\'n}ski, Adam and Ong, Luke and Rainforth, Tom},
    booktitle = {Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence},
    year = {2022}
  }