Sam Greydanus

greydanus.github.io · Personal blog · on HN since 2017

Sam Greydanus is a machine learning researcher who writes about physics-inspired neural networks, small-scale deep learning, and optimization.

Visit blog ↗ RSS HN submissions ↗

What HN saysCommenters call it a beautiful blog and single out the wing optimization and scaling-down posts as favorites.

22HN people shared it

6linked it in comments

20stories submitted

495story points

7 months agolast shared

2017people per year2026

Most-shared posts

dysoco · 2024-09-11

I remember John Carlos Baez having some interesting stuff: https://johncarlosbaez.wordpress.com/ Some other ones I had bookmarked the other day but haven't seen much in depth, mostly computer science based but more towards theory/math side: https://blog.computationalcomplexity.org/ https://semantic-domain.blogspot.com/ https://greydanus.github.io/ Also go to Terry Tao's blog and look at the sidebar, there are a lot of links to external blogs there.

naillo · 2022-12-22

This is a beautiful blog, e.g. this one is one of my favorites https://greydanus.github.io/2020/10/14/optimizing-a-wing/

gwern · 2025-04-30

Some of the older posts are very cute. I enjoyed https://greydanus.github.io/2020/12/01/scaling-down/ on showing how many high-powered tricks you can do with a tiny NN of the sort that will train in seconds.

CGamesPlay · 2023-01-18

This is somewhat related: how do we build datasets that are better discriminators of model architectures, and are also easier to experiment on? https://greydanus.github.io/2020/12/01/scaling-down/

xorand · 2020-03-12

I found the previous Hamiltonian Neural Networks [0]. If the authors are here, I'd be interested to use [1] for a version with dissipation. [0] https://greydanus.github.io/2019/05/15/hamiltonian-nns/ [1] https://arxiv.org/abs/1902.04598

brudgers · 2017-08-11