Peter Richtarik
@peter_richtarik
Federated Learning Guru. Tweeting since 20.5.2020. Lived in 🇸🇰🇺🇸🇧🇪🇬🇧🇸🇦
It is perhaps helpful to recall Nesterov’s opinion: nccr-automation.ch/news/2023/unpr…
Apply for the AITHYRA-CeMM International PhD Program! 15-20 fully funded PhD fellowships available in Vienna in AI/ML and Life Sciences Deadline for applications: 10 September 2025 apply.cemm.at
All the papers in my AC batch are <= 3.5. It probably depends a lot on the topic area 🙂
Some SAC context for NeurIPS review scores - out of my batch of 100 papers: - 1 paper ≥5.0 - 6 papers ≥4.5 - 11 papers ≥4.0 - 25 papers ≥3.75 - 42 papers ≥3.5 So currently naive accept cutoff would be 3.75.
🧵 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…
🧵 In our last thread, we talked about learning to reason-and how reasoning is fundamentally search under uncertainty. But here’s the catch: our data (proofs, code, textbook solutions) shows only the final successful path. Not the trial and error. So how can we learn to reason…
🧵 In our earlier threads, we explored what it means to learn to reason, why it’s hard, and why many current approaches fall short. Now let’s dive into one of the core proofs from our paper. Appendix A of our paper shows that an auto-regressive transformer cannot learn to…
Looking for postdocs to join my Optimization & Machine Learning Lab @ KAUST! Write to me by the end of November 2025 if you want to apply. richtarik.org richtarik.org/i_papers.html richtarik.org/i_team.html richtarik.org/i_join.html
Ready to turn your research into global impact? Join the KAUST Global Fellowship Program and help shape the future of science and innovation, advance your independent research career, and tackle global challenges at a world-class university.
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…
1/N I’m excited to share that our latest @OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the world’s most prestigious math competition—the International Math Olympiad (IMO).
The theory behind deep learning optimizers often lags behind practice, especially for new methods. Muon (@kellerjordan0) & Scion (@tmpethick et al.) show great results on LLMs which motivated us to take a closer look and work toward bridging this theory–practice gap.
🚀 Join @MBZUAI (Abu Dhabi) to advance efficient & distributed ML! 🔹 Postdoctoral Associate — apply.interfolio.com/170202 🔹 Visiting Student — apply.interfolio.com/170203 Apply now and help shape the future of #MachineLearning. #AI #Postdoc #PhD #Careers
Poster with @ArtoMaranjyan @emsaad_p, and @peter_richtarik
I have another poster tomorrow. It’s related to Ringmaster—come check it out!
MIT's "Street Fighting Mathematics" This course teaches the art of guessing results and solving problems without doing a proof or an exact calculation. readings: ocw.mit.edu/courses/18-098…… (audio generated by NotebookLM)