NeurIPS 2021 - The Austrian Contributions

ℹ️ Keep-Current Meetup was selected as an official NeurIPS 2021 Meetup. ℹ️

To highlight the Austrian contribution, we dedicate this meetup to the researchers whose papers were accepted to The conference!

The NeurIPS conference this year is held online 💻, and since we are in a lockdown anyway in Austria, let's turn this into an opportunity to get updated about the newest Machine Learning Research - from the researches themselves!

⚠️ By participating in this meetup, you are obligated to follow the NeurIPS code of conduct: https://neurips.cc/public/CodeOfConduct

✨✨✨

🎓 Mathias Lechner, Machine Learning Researcher and a PhD candidate @ IST Austria will explain about two of his papers which were accepted:
"Infinite Time Horizon Safety of Bayesian Neural Networks" - https://papers.nips.cc/paper/2021/hash/544defa9fddff50c53b71c43e0da72be-Abstract.html

"Causal Navigation by Continuous-time Neural Networks" - https://papers.nips.cc/paper/2021/hash/67ba02d73c54f0b83c05507b7fb7267f-Abstract.html

🔬 Ramin Hasani, Postdoctoral Associate at MIT, will tell us about his research:
"Sparse Flows: Pruning Continuous-depth Models" - https://arxiv.org/abs/2111.04714

🎓 Rahim Entezari, Ph.D. Candidate at TU Graz/Complexity Science Hub, will talk about his research: The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
https://arxiv.org/pdf/2110.06296.pdf

🔬 Researchers from IST Austria, will give us details about their research:

Elias Frantar: "M-FAC: Efficient Matrix-Free Approximations of Second-Order Information" - https://arxiv.org/abs/2107.03356

Alexandra Peste: "AC/DC: Alternating Compressed/Decompressed Training of Deep Neural Networks" - https://arxiv.org/abs/2106.12379

Giorgi Nadiradze: "Fully-Asynchronous Decentralized SGD with Quantized and Local Updates" https://proceedings.neurips.cc/paper/2021/hash/362c99307cdc3f2d8b410652386a9dd1-Abstract.html

🎓 Werner Zellinger from SCCH - Software Competence Center Hagenberg will present his paper:
"The balancing principle for parameter choice in distance-regularized domain adaptation" https://papers.nips.cc/paper/2021/hash/ae0909a324fb2530e205e52d40266418-Abstract.html

and Kajetan Schweighofer from Kepler Universität Linz will present their workshop paper:
"Understanding the Effects of Dataset Composition on Offline Reinforcement Learning" https://arxiv.org/abs/2111.04714

🔬 Viktoriia Korchemna, the awarded researcher from TU Wien, will present her work: "The Complexity of Bayesian Network Learning: Revisiting the Superstructure" - https://papers.nips.cc/paper/2021/hash/040a99f23e8960763e680041c601acab-Abstract.html

✨✨✨

The event will be broadcast live on YouTube.

We look forward to seeing you (online)!

🎄🎄🎄