Dilsad Er

I am a Doctoral Researcher at the Max Planck Institute for Intelligent Systems. My research focuses on communication-efficient distributed learning and system-theoretic approaches to algorithm analysis. I have experience in control theory, optimization, and machine learning.

I actively contribute to outreach initiatives, including Tübingen Women in Machine Learning and Soapbox Science, promoting diversity and public engagement in STEM.

For more details, visit my Google Scholar or LinkedIn.

news

Aug 01, 2025	Our workshop "DynaFront: Dynamics at the Frontiers of Optimization, Sampling, and Games" is accepted to NeurIPS 2025 in San Diego. Details and submission info here: Website.
Jun 10, 2025	Course materials for our hands-on machine learning workshop with LEGO SPIKE are now available. Check them out here: [Videos], [Website]
May 01, 2025	Our work "Distributed Event-Based Learning via ADMM" is accepted to International Conference on Machine Learning (ICML) 2025!
Apr 15, 2025	We held the second round of our hands-on Machine Learning workshop at KI Makerspace Tübingen, where young learners once again built LEGO-based robots and trained their own machine learning models. We will soon publish the full course material and videos on our YouTube channel. So stay tuned if you want to follow along . Many thanks to KI Makerspace for supporting this initiative and to all the participants for their energy and curiosity!
Mar 14, 2025	We have organized the 3rd TWiML Workshop, bringing together an engaged community of learners and researchers for another inspiring session: Machine Learning for Science
Mar 04, 2025	We successfully conducted a hands-on Machine Learning workshop at KI Makerspace Tübingen, where young learners built and interacted with machine learning models using LEGO-based robots. Students collected their own datasets and visualized the models' performance on a web-based interface. The event was met with enthusiasm, sparking curiosity about AI and robotics! Special thanks to KI Makerspace for hosting and to all participants for their engagement!

selected publications

ICML

Distributed Event-Based Learning via ADMM

G. D. Er, S. Trimpe, and M. Mühlebach

To appear in International Conference on Machine Learning (ICML), 2025

Bib

@article{er2024admm,
  title = {Distributed Event-Based Learning via ADMM},
  author = {Er, G. D. and Trimpe, S. and Mühlebach, M.},
  year = {2025},
  journal = {To appear in International Conference on Machine Learning (ICML)},
  url = {https://arxiv.org/abs/2405.10618}
}