Do you want to do a Postdoc developing new methods/theory in Optimization for deep learning/ML? Do you enjoy bluesky open research and discussions on black boards? Then Apply to the Flatiron Fellowship in the Center of Computational Mathematics https://t.co/ydXX28xmAd 1/3
The blog option was more popular than I had imagined. So be it, I will start a blog, and start with a series on "Muon through the lens of Robustness", "Stochastic whitening as a design principle" and "Curvature for non-convex problems". I'll also write the stuffy papers.
I've been thinking a lot about different adaptive methods such as shampoo, KLshampoo, PSGD, quasi-Newton methods, Adam ... and now have figured some really nice connections. How should I tell everyone about this?
I'm looking to recruit PhD students for Fall 2027 interested in probabilistic machine learning methods and AI for science, especially in domains such as chemistry, physics, and biology.
Apply to the Cornell CS PhD program & list my name on your application.
Due Dec 15! Please share. More info below:
📣 We are excited to announce the workshop
Emerging Directions in Probabilistic Modeling: Methods and Scientific Applications
📅 Oct. 5–7, 2026
📍 Flatiron Institute & IBM Research, NYC
Applications are welcome by Aug. 22:
https://t.co/Ql4O8H2WyW
I am looking for the amazing postdocs to advance the foundations of optimization, machine learning, and AI.
Requirement:
- Outstanding training and track record in mathematics and computer science. - Stellar research track record in optimization, ML and AI, a closely related field.
Supplementary info: https://t.co/SOJ0k2p59Q
@nikhilghosh101@nikhilghosh101 was the driving force behind this— deriving the method to running the experiments. He was determined to make something that works at scale and beats Adam in both time and steps. Try his code and watch your GPUs go brrr: https://t.co/hC1046rGLJ
We've been working for about a year now on how to port the core idea of Muon to LoRA (low rank) finetuning. If you're interested in Muon, preconditioned Muon, Lora, let me tell you about what we learned and our PoLoRA method https://t.co/q9gVJ31lkU
https://t.co/pBrnAfatd9
We have a lot of experiments and tests in the paper on learning rate transfers, different data sets from Math, coding to Bengali! Check out our paper,
https://t.co/KvHRk9xWGB
and blogpost for. more
https://t.co/pBrnAfatd9
Work led by @nikhilghosh101 and Tetiana Parshakova.