⚠️ The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret

By Lukas Fluri*, @leon-lang.bsky.social *, Alessandro Abate, Patrick Forré, David Krueger, Joar Skalse

📜 arxiv.org/abs/2406.15753

🧵6 / 8

🔁 SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations

By @gbarto.bsky.social , Dmitry Vetrov, @canaesseth.bsky.social

📜 arxiv.org/abs/2502.02472

🧵5 / 8

📐 On the Importance of Embedding Norms in Self-Supervised Learning

By Andrew Draganov, @sharvaree.bsky.social , Sebastian Damrich, Jan Niklas Böhm, Lucas Maes, Dmitry Kobak, @erikjbekkers.bsky.social

📜 arxiv.org/abs/2502.09252

🧵4 / 8

⚖️ A machine learning approach to duality in statistical physics

By Prateek Gupta, Andrea Ferrari, @nabiliqbal.bsky.social

📜 arxiv.org/abs/2411.04838

🧵3 / 8

The Christmas spirit has arrived at AMLab! 🎄✨
Yesterday we kicked off the holidays with a festive group dinner and a fun Secret Santa exchange. 🎅

Wishing everyone a restful and joyful winter break and a happy new year! ❄️💫

Professor Imbens also had a mentoring session with our PhD students actively working on causality, discussing their ideas and the potential impact of their applications! 👨‍🔬👩‍🔬

@matyasch.bsky.social @roelhulsman.bsky.social @rmassidda.it @danruxu.bsky.social 🔥

Yesterday, we had the honor of hosting 2021 Nobel Laureate in Economics, Guido Imbens, at our Lab! 🤩

We had the chance to attend his inspiring talk on Experimental Design in Marketplaces 📈👩‍💻

A big thank you to @smaglia.bsky.social for making this event possible 💥

Yesterday the Amsterdam Causality Meeting took place at LAB42, hosted by @ellisamsterdam.bsky.social and co-organized by @smaglia.bsky.social 💥

We attended inspiring talks by @rmassidda.it , currently visiting AMLab, and @phillip-lippe.bsky.social 🤩

👩‍💻 Slides: amscausality.github.io/upcoming/ 👩‍💻

Thanks to the organizers and participants for such an inspiring event and poster session! 🤩

The drinks and snacks were also well appreciated, as @maxxxzdn.bsky.social demonstrates 😉

During the poster session, AMLab members presented their NeurIPS papers. 🇨🇦

If you will also be in Vancouver, make sure to check them out! 🧐

Yesterday @ellisamsterdam.bsky.social hosted the yearly NeurIPS-Fest, a pre-party for NeurIPS with a keynote talk, poster session, drinks and bites! 🍺🍻

The keynote was by @canaesseth.bsky.social , who talked about "Diffusion, Flows and other stories", presenting his 5 papers accepted at NeurIPS! 💥

Thanks to the organizers and the speakers for the inspiring Geometry-Grounded Representation Learning (NeurReps) seminar that happened yesterday! 🤩

🚨 In case you missed it 🚨 the talk was recorded and it will be available soon at this link: www.neurreps.org/past-seminars

Soon, @erikjbekkers.bsky.social and @davidmknigge.bsky.social will give a talk elaborating even further on geometry-grounded representation learning in a NeurReps seminar. Make sure to mark the date! :)

⏰ November 21st, 4 PM CET
🔗 www.neurreps.org/speaker-seri...

Yesterday, @erikjbekkers.bsky.social presented his vision on equivariance to IvI (at UvA), showcasing recent work on geometry-grounded representation learning - addressing fundamental limitations in geometric reasoning of current AI systems. 🤖
Exciting times ahead for geometric deep learning! 🌐 🤩