The NeurIPS paper checklist corroborates the bureaucratic theory of statistics. argmin.net/p/standard-err…

🏹 Job alert: Research Associate or Research Fellow in Probabilistic Machine Learning 📍Manchester 🏴󠁧󠁢󠁥󠁮󠁧󠁿 📅 Apply by July 27 bit.ly/3TH28xZ

🚨 In other news, a paper titled "Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks" has been accepted in TMLR and the final camera-ready version is now up in OpenReview. Transactions on Machine Learning Research Accepted papers at TMLR openreview.net/forum?id=ABT1X…

The diagram commutativity proof argument

🚨 Still time to apply for Research Associate and Research Fellow positions in probabilistic ML with the Manchester Centre for AI Fundamentals. The deadline is 27.July. 2025⌛️

🧵 What does it mean to learn from data-with guarantees? And what does it mean to learn to reason-with guarantees? In 1984, Leslie Valiant proposed the Probably Approximately Correct (PAC) model, laying the foundation of modern learning theory. In a recent paper with

New post on the Learning Theory Alliance blog, by Arsen Vasilyan. This covers the recently introduced testable learning paradigm of Rubinfeld and Vasilyan, from their STOC 2023 paper. It's a great chance to catch up on all the exciting work that's happened in this area!

Advanced version of Gemini Deep Think (announced at #GoogleIO) using parallel inference time computation achieved gold-medal performance at IMO, solving 5/6 problems with rigorous proofs as verified by official IMO judges! Congrats to all involved! deepmind.google/discover/blog/…

Official results are in - Gemini achieved gold-medal level in the International Mathematical Olympiad! 🏆 An advanced version was able to solve 5 out of 6 problems. Incredible progress - huge congrats to Thang Luong and the team! deepmind.google/discover/blog/…

🚨 One week left to submit contributed talks, posters, and tutorials to the ML in PL Conference 2025! Don't miss your chance to present at this year's conference: 👉 Main Conference talks and posters (October 15-17, 2025) 👉 Tutorials (October 18, 2025) ✓ Talk and poster

📢 Call for Papers - The Artificial Intelligence in Science Summit 2025, supported by ELLIS Unit Copenhagen 🇩🇰, invites submissions to the Poster and Demonstration Track. 📖 Submission deadline: Sep 1 📅 Summit: Nov 3-4 📍 Copenhagen 🇩🇰 ellis.eu/events/ai-in-s…

Mila's proud to support Deep Learning Indaba 2025 in Rwanda! This pivotal African AI event will convene over 600 experts, fostering keynotes, workshops, and vital discussions on responsible AI and empowering African voices. A Mila delegation will be on site to present their

Day 3 continues with the oral presentations about Causality! 👉 auai.org/uai2025/schedu…

🚨 A few days left to apply for Research Associate and Research Fellow positions in probabilistic machine learning with the Manchester Centre for AI Fundamentals. The deadline is 27.July. 2025⌛️

✨ The 2025 Joint LMS/@imamaths conference takes place on 25 Sep at University of Manchester Department of Mathematics and online. ''Securing the Twenty-First Century Internet' brings together experts from mathematics and cybersecurity to highlight current research developments in area. ➡️ lms.ac.uk/events/lms-ima…

There is an opening for a University Assistant Professor in Machine Learning to be based at Cambridge MLG jobs.cam.ac.uk/job/49361/ Apply!

Finally, a good modern book on causality for ML: causalai-book.net by Elias Bareinboim. This looks like a worthy successor to the ground breaking book by Judea Pearl which I read in grad school. (h/t Joshua Safyan for the ref).

📅 You're invited! Join us for the Rothschild Fellow Public Lecture by Professor Subhashis Ghoshal: "Immersion posterior: Meeting Frequentist Goals under Structural Restrictions", 5 August 2025, at 4 PM in Seminar Room 1. #isaacnewtoninstitute #newtonrcl2025 #publiclecture