Werner Zellinger retweeted
I am very happy to share the first paper of my PhD:
SIMSHIFT - A Benchmark for Adapting Neural Surrogates to Distribution Shifts
1/n
We introduce SIMSHIFT: A Benchmark for Adapting Neural Surrogates to Distribution Shifts. I sincerely hope that new ideas are coming out from this benchmark.
Paper: arxiv.org/abs/2506.12007
Code: github.com/psetinek/simshift
Werner Zellinger retweeted
We introduce SIMSHIFT: A Benchmark for Adapting Neural Surrogates to Distribution Shifts. I sincerely hope that new ideas are coming out from this benchmark.
Paper: arxiv.org/abs/2506.12007
Code: github.com/psetinek/simshift
Werner Zellinger retweeted
I will be speaking about our recent series of papers on learning in infinite dimensions!
Joint Seminar on Inverse Problems and Learning Theory on Oct 29, 14:00 CET (online).
Seminar homepage:
sites.google.com/view/joint-…
🧵Accepted at @NeurIPSConf #NeurIPS2024
Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
We extend our analysis of regularized learning in infinite dimensions from NeurIPS '22 and JMLR '24 to more general learning algorithms.
Werner Zellinger retweeted
📢 I would like to draw your attention to our seminar on
** Inverse Problems and Learning Theory **
sites.google.com/view/joint-…
Werner Zellinger retweeted
The Joint Seminar on Inverse Problems and Learning Theory is a presentation-based online space for discussing research at the intersection of: Inverse Problems, Learning Theory, Statistics, Information Theory and Machine Learning. Everyone interested is welcome!
Werner Zellinger retweeted
🚀 SymbolicAI – a framework for logic-based approaches combining generative models and solvers. Alongside, we introduce a benchmark and empirical measure to evaluate SOTA LLMs in AI-centric workflows. Read more in our paper arxiv.org/abs/2402.00854 #MachineLearning 🧠💡[1/n]
Werner Zellinger retweeted
OPEN POSITIONS!
We have open positions for PhD students and PostDocs at my lab both in core machine learning as well as in "Machine Learning in Life Sciences":
jku.at/en/lit-artificial-int…
Werner Zellinger retweeted
For people @iclr_conf, Clifford Neural Layers for PDE Modeling air today at #130 from 11:30 onwards. Happy to chat about Clifford or geometric algebras, (large-scale) PDE modeling, or anything related!
microsoft.github.io/clifford…
Meet us at 15:00 for our oral presentation at ICLR in room AD12.
arxiv.org/abs/2305.01281
Werner Zellinger retweeted
Our paper "Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation" has been selected for oral presentation (notable-top-5%) at #ICLR2023 openreview.net/forum?id=M95o…. [1/n]













