Marek Wydmuch


I'm Marek Wydmuch

Ph.D. student at Poznan University of Technology, Poland, interested mostly in various Machine Learning topics. My current research is focused on Extreme Classification. I'm supervised by Krzysztof Dembczyński. I
I stand with Ukraine 🇺🇦

These are some of the things I've made and done:

  • 11.2022Me and ViZDoom project joined The Farama Foundation.
  • 06.2022I started an internship at Yahoo! in Paris, France.
  • 05.2022Our paper titled "On missing labels, long-tails and propensities in extreme multi-label classification" was accepted at KDD'22.
  • 03.2022New release of ViZDoom (1.1.12) library with new official OpenAI Gym wrapper.
  • 01.2022I joined the management board of ML in PL Association.
  • 11.2021New release of ViZDoom (1.1.11) library with new features, including access to the game's audio buffer.
  • 08.2021Our paper "ViZDoom Competitions: Playing Doom From Pixels" received 2022 IEEE ToG Outstanding Paper Award.
  • 04.2021Our short paper titled "Propensity-scored Probabilistic Label Trees" was accepted at SIGIR'21.
  • 03.2021Our paper titled "Efficient Set-Valued Prediction in Multi-Class Classification" was accepted for publication in Data Mining and Knowledge Discovery.
  • 02.2021Our paper titled "Online probabilistic label trees" was accepted at AISTATS'21.
  • 12.2020I gave a talk titled "Probabilistic Label Trees in Vowpal Wabbit" on Vowpal Wabbit Workshop at NeurIPS'20. [ video]
  • 10.2020I gave a talk titled "Extreme classification: applications and algorithms" on GHOST Day: AMLC'20. [ video]
  • ViZDoom - Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information.
  • napkinXC - extremely simple and fast library for extreme multi-class and multi-label classification.
  • extremeText - extension of fastText library for multi-label classification including extreme cases with hundreds of thousands and millions of labels.

I'm proud to be a member of the awesome ML in PL Association, a non-profit organization devoted to fostering the machine learning community in Poland and around the world.

I co-organized ML in PL Conference 2019, ML in PL Virtual Event 2020, and ML in PL Conference 2021 serving as Call for Contributions (Talks and Posters) coordinator.

From 2021 I'm a member of the management board of ML in PL Association and try to support other members of the association in the organization of great machine learning events.

I try to review at least a dozen of papers each year. So far I served as a reviewer for:
I am/was teaching a few courses at Poznan University of Technology:
  • Advanced Methods of Computational Intelligence 2021 and 2022 (lectures + exercises)
    based on Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction and selected chapters from Stuart Russell and Peter Norvig, Artificial Intelligence A Modern Approach.
  • Methods of Artificial and Computational Intelligence 2021 (exercises)
    based on selected chapters from Stuart Russell and Peter Norvig, Artificial Intelligence A Modern Approach.
  • Big Data Processing 2019/2020 and Processing of Massive Datasets 2018/2019 (exercises)
    based on selected chapters from Jure Leskovec, Anand Rajaraman, Jeff Ullman, Mining of Massive Datasets.
  • Information Theory and Lossless Compression Methods 2018 (exercises)
    based on the first chapters from David J.C. MacKay, Information Theory, Inference, and Learning Algorithms.
If you are my student feel free to contact me via e-mail.