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.
These are some of the things I've made and done:
- 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]
Propensity-scored Probabilistic Label Trees
Marek Wydmuch, Kalina Jasinska-Kobus, Rohit Babbar, Krzysztof Dembczyński
Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021
[ code (napkinXC)] [ paper] [ poster] [ bibtex]
Online probabilistic label trees
Kalina Jasinska-Kobus, Marek Wydmuch, Devanathan Thiruvenkatachari, Krzysztof Dembczyński
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
[ code (napkinXC)] [ paper] [ poster] [ AISTATS 2021 talk] [ ICML XC 2020 talk] [ bibtex]
Efficient set-valued prediction in multi-class classification
Thomas Mortier, Marek Wydmuch, Krzysztof Dembczyński, Eyke Hüllermeier, Willem Waegeman
Data Mining and Knowledge Discovery, 2021
[ paper] [ bibtex]
Probabilistic Label Trees for Extreme Multi-label Classification
Kalina Jasinska-Kobus, Marek Wydmuch, Krzysztof Dembczyński
Submitted to Journal of Machine Learning Research, 2020
[ code (napkinXC)] [ bibtex]
A no-regret generalization of hierarchical softmax to extreme multi-label classification
Marek Wydmuch, Kalina Jasinska-Kobus, Mikhail Kuznetsov, Robert Busa-Fekete, Krzysztof Dembczyński
Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS), 2018
[ code (extremeText)] [ paper] [ poster] [ bibtex]
ViZDoom Competitions: Playing Doom From Pixels
Marek Wydmuch, Michał Kempka, Wojciech Jaśkowski
IEEE Transactions on Games, 2018
Note: 2022 IEEE ToG Outstanding Paper Award
[ paper] [ movies] [ bibtex]
ViZDoom: A Doom-based AI research platform for visual reinforcement learning
Michał Kempka, Marek Wydmuch, Grzegorz Runc, Jakub Toczek, Wojciech Jaśkowski
2016 IEEE Conference on Computational Intelligence and Games (CIG), 2016
Note: 2016 IEEE CIG The Best Paper Award
[ www] [ code] [ paper] [ bibtex]
- 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 ML in PL Association, a non-profit organization devoted to fostering the machine learning community in Poland and around the world.
From 2021 I'm a member of the management board of ML in PL Association.
- ICML 2020, 2021, and 2022
- NeurIPS 2020, and 2021 (Outstanding Reviewer Award)
- AISTATS 2021
- IJCAI 2020, and 2021
- ICLR 2022
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Machine Learning Journal