Paul Häusner

Ella J. Schmidtobreick, Daniel Arnstr\"om, Paul H\"ausner, Jens Sj\"olund: Warm-starting active-set solvers using graph neural networks https://arxiv.org/abs/2511.13174 https://arxiv.org/pdf/2511.13174 https://arxiv.org/html/2511.13174

🔄 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.

NeurIPS participation in Europe We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...

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.

Jens Sjölund giving the opening remarks for the LoG meetup

Audience of the LoG meetup

Poster session at the LoG meetup

Organizing team of the LoG meetup

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.

LoG Meetup Sweden A two-day workshop to bring together people from academia and industry working on machine learning with graphs and geometry. The official LoG conference meetup in Sweden

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...

Neural incomplete factorization: learning preconditioners for the... The convergence of the conjugate gradient method for solving large-scale and sparse linear equation systems depends on the spectral properties of the system matrix, which can be improved by...

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...