🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

The Davis-Kahan sin(θ) theorem bounds the difference between the subspaces spanned by eigenvectors of two symmetric matrices, based on the difference between the matrices. It quantifies how small perturbations in a matrix affect its eigenvectors. jstor.org/stable/2949580…

Introducing M.S. in Mathematical Data Science at USC Dornsife. Now accepting applications!! youtu.be/ELOFHqe2BFs?si… via YouTube

I have an opening for a two year postdoc position at Harvard. The application link: academicpositions.harvard.edu/postings/14420

Excited about our progress in characterizing The Computational Advantage of Depth in Learning with Neural Networks. Check out the number of samples that can be saved when GD runs on a multi-layer rather than on a two-layer neural network. arxiv.org/pdf/2502.13961

I'm glad that my paper on LLMs is published in the prestigious journal PNAS. The main finding is that LLMs represent compositions and achieve OOD generalization using latent subspaces so that multiple self-attention layers are aligned. See the blog post: yiqiao-zhong.github.io/jekyll/update/…

I'm trying to compile a reading list for math graduate students, on existing/popular theories of generalization in deep learning. I can think of tens of beautiful research articles, but any book / survey you would recommend? Any suggestion would be appreciated!

"This is one of the first results where a neural model, when trained to sufficiently low loss, can 𝐠𝐮𝐚𝐫𝐚𝐧𝐭𝐞𝐞 𝐎𝐎𝐃 𝐬𝐢𝐳𝐞 𝐠𝐞𝐧𝐞𝐫𝐚𝐥𝐢𝐳𝐚𝐭𝐢𝐨𝐧 for a non-linear algorithm" ... 🤯

For those that couldn't make it, we've uploaded our full STOC workshop on High Dimensional Expanders to Youtube! Hopefully a useful resource for learning the basics of HDX and how they're applied in TCS. Talk 1: An introduction to HDX youtube.com/watch?v=r6mrG3…