🔄 Updated Arxiv Paper

Title: Learning to accelerate distributed ADMM using graph neural networks
Authors: Henri Doerks, Paul H\"ausner, Daniel Hern\'andez Escobar, Jens Sj\"olund

Read more: https://arxiv.org/abs/2509.05288

I’m happy to share that I’ll be spending the fall semester at Princeton as a visiting student in the Department of Operations Research and Financial Engineering (ORFE), working with @stellato.io funded through the WASP program. If you’re in the area and would like to connect, feel free to reach out.

Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)

I’d also like to extend my gratitude to my fellow organizers Jens Sjölund (@jsjol.bsky.social) , Elias Nyholm and Sebastian Mair for making this happen. Looking forward to building on this momentum!

A huge thank you to everyone who participated—your contributions made this an inspiring and insightful event! We had two exciting keynote talks by @smnlssn.bsky.social and Kathlén Kohn, along with a diverse lineup of contributed talks and posters from participants around Scandinavia.

This week, we had the pleasure of hosting Sweden’s first @logconference.bsky.social meetup at Uppsala University! Over two days, we brought together researchers and industry professionals working at the intersection of machine learning, graphs, and geometry.

Also don’t forget to sign up for our LoG meetup that is taking place in February at Uppsala University 🇸🇪! We’ll have some great keynotes and there are still slots for contributed presentations and posters.

sites.google.com/view/logmeet...

Hej 🦋! I’m happy to share that our latest TMLR paper that uses graph neural networks to learn incomplete factorization preconditioners for the conjugate gradient method has been accepted as an oral presentation at next week’s Learning on Graphs (LoG) conference!

openreview.net/forum?id=Foz...