Jason Lee
@jasondeanlee.bsky.social
1.5K followers 2.1K following 12 posts
Associate Professor at Princeton Machine Learning Researcher
Posts Media Videos Starter Packs
jasondeanlee.bsky.social
Our new work on scaling laws that includes compute, model size, and number of samples. The analysis involves an extremely fine-grained analysis of online sgd built up over the last 8 years of understanding sgd on simple toy models (tensors, single index models, multi index model)
eshaannichani.bsky.social
Excited to announce a new paper with Yunwei Ren, Denny Wu,
@jasondeanlee.bsky.social!

We prove a neural scaling law in the SGD learning of extensive width two-layer neural networks.

arxiv.org/abs/2504.19983

🧵below (1/10)
Reposted by Jason Lee
standupforscience.bsky.social
Welcome to the Bluesky account for Stand Up for Science 2025!

Keep an eye on this space for updates, event information, and ways to get involved. We can't wait to see everyone #standupforscience2025 on March 7th, both in DC and locations nationwide!

#scienceforall #sciencenotsilence
jasondeanlee.bsky.social
Duck in Vancouver! Mott32
Reposted by Jason Lee
docmilanfar.bsky.social
“On a log-log plot, my grandmother fits on a straight line.”
-Physicist Fritz Houtermans

There's a lot of truth to this. log-log plots are often abused and can be very misleading

1/5
Reposted by Jason Lee
quanquangu.bsky.social
Just put together a starter pack for Deep Learning Theory. Let me know if you'd like to be included or suggest someone to add to the list!

go.bsky.app/2qnppia
jasondeanlee.bsky.social
Zihan Zhang (tinyurl.com/4nks7f9b) is a postdoc with Yuxin Chen, Simon Du, and me.
jasondeanlee.bsky.social
What's known about the 1.27 lower bound? It's a guess or there is a reason ppl believe it's fundamental?
jasondeanlee.bsky.social
What's the point of @perplexity_ai given chatgpt also does search?
jasondeanlee.bsky.social
Yo add me to your starter packs!
Reposted by Jason Lee
andrea-montanari.bsky.social
Assume that the nodes of a social network can choose between two alternative technologies: B and X.
A node using B receives a benefit with respect to X, but there is a benefit to using the same tech as the majority of your neighbors.
Assume everyone uses X at time t=0. Will they switch to B?
Spread of innovation in a small world network.
jasondeanlee.bsky.social
Takes too much clicking...
jasondeanlee.bsky.social
How do I bulk follow people?