Why do you hate the boat so much?

Couldn’t agree more with Amin Karbasi : 90 secs well spent!

ZIB is turning 40 this year. Celebrate with us! pokutta.com/blog/news/2024…

#optimization #ml #researchpapers #pagerank Hi everyone, I have just released a video on a beautiful optimization paper, based on an accelerated gradient descent method to solve the Sparse PageRank problem. Make sure to check it out: youtu.be/kLFNNqrp3DA?si…

On my way to Vienna for #ICLR2024 with our paper "Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging". We address the challenge of creating Model Soups from Sparse Neural Networks while preserving their sparsity patterns! arXiv: arxiv.org/abs/2306.16788 🧵1/n

Really happy to be part of this international and interdisciplinary collaboration! Our #ICML24 camera-ready paper is now available on arXiv: arxiv.org/abs/2406.01076 TLDR-blogpost will follow! See you in Vienna!

🌟 Join our Team in Berlin 🌟 We are seeking highly motivated PhD students to work on (efficient) Deep Learning, preferably with strong math/CS background and PyTorch experience. Happy to answer questions here, via DM or at #icml2024! Apply at iol.zib.de/openings! Please RT

A good time to share our #ICLR2023 paper: How I Learned to Stop Worrying and Love Retraining We explore sparsity-adaptive LR schedules and show that with proper LR care, simple pruning can outperform complex methods that 'learn' the sparsity. 📜 arxiv.org/abs/2111.00843 🧵1/n

Short summary of our recent paper on adversarial defenses vs watermarking together with Sai Ganesh Nagarajan Berkant Turan and Grzegorz Gluch - you gotta get at most one. pokutta.com/blog/research/… #machinelearning #watermarks #adversarialdefense

Short summary of our recent paper “On the Byzantine-Resilience of Distillation-Based Federated Learning” with Christophe Roux and Max Zimmer. pokutta.com/blog/research/… #ml #ai #federatedlearning

Looking forward to seeing everyone!

We just released: Foundation-Sec-8B, an open-weight, 8-billion-parameter base model purpose-built for cybersecurity.  Why it’s special: State-of-the-art in a small package: performs on par with—or even ahead of—models many times its size (e.g., Llama-3.1-70B) on CTI-MCQA and

Spotlight: Neural Discovery in Mathematics: Do Machines Dream of Colored Planes? arxiv.org/abs/2501.18527 w/ K. Mundinger, A. Kiem, C. Spiegel & Sebastian Pokutta

Poster: Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation arxiv.org/abs/2501.19328 Blogpost: maxzimmer.org/blog/2025/capt… w/ Jan Pauls, Berkant Turan, S. Saatchi, Philippe.ciais, Sebastian Pokutta & F. Gieseke

Poster: Approximating Latent Manifolds in Neural Networks via Vanishing Ideals arxiv.org/abs/2502.15051 w/ N. Pelleriti, E. Wirth & Sebastian Pokutta

Will be at #AISTATS2025 in Phuket, reach out if you are looking for PhD positions!

Our #AI4Science paper "Capturing Temporal Dynamics in Canopy Tree Height" is accepted at #ICML2025! We present the first 10m temporal map for Europe (2019-22), improving tall tree estimation & tracking change. Blog: maxzimmer.org/blog/2025/capt… Paper: arxiv.org/abs/2501.19328 🧵 1/7

🎉Our paper "Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?" was selected for an ORAL (top 1%) presentation at #ICML25! 🎉 arXiv: arxiv.org/abs/2501.18527 blog: maxzimmer.org/blog/2025/neur… 🧵: coming soon

My brilliant student Anay Mehrotra and amazing post-doc Alkis Kalavasis just won the Best Paper Award at COLT 2025! Clearly, they’ve cracked the code: do great math, write a killer paper, take home the trophy. Huge congratulations to both of them. Now please don’t forget your

It’s hard to overstate the significance of this. It may end up looking like a “moon‑landing moment” for AI. Just to spell it out as clearly as possible: a next-word prediction machine (because that's really what it is here, no tools no nothing) just produced genuinely creative