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)

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

Duck in Vancouver! Mott32

“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

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

Lool

Settling the Sample Complexity of Online Reinforcement Learning A central issue lying at the heart of online reinforcement learning (RL) is data efficiency. While a number of recent works achieved asymptotically minimal regret in online RL, the optimality of these...

Representative results:
Settling the sampling complexity of RL: arxiv.org/abs/2307.13586
Optimal Muti-Distribution Learning (solved a COLT 2023 open problem): arxiv.org/abs/2312.05134
Anytime Acceleration of Gradient Descent (solved a COLT 2024 open problem): arxiv.org/abs/2411.17668

Zihan Zhang (tinyurl.com/4nks7f9b) is a postdoc with Yuxin Chen, Simon Du, and me.

What's known about the 1.27 lower bound? It's a guess or there is a reason ppl believe it's fundamental?

Send your colt open problems to Zihan, with high probability he will solve it!

Anytime Acceleration of Gradient Descent This work investigates stepsize-based acceleration of gradient descent with {\em anytime} convergence guarantees. For smooth (non-strongly) convex optimization, we propose a stepsize schedule that all...

arxiv.org/abs/2411.17668 Our postdoc zihan slays another COLT open problem! proceedings.mlr.press/v247/kornows...

What's the point of @perplexity_ai given chatgpt also does search?

Yo add me to your starter packs!

Spread of innovation in a small world network.

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?

Sky Follower Bridge - Chrome Web Store Instantly find and follow the same users from your Twitter follows on Bluesky.

Starter packs are helpful as well as the twitter import tool chromewebstore.google.com/detail/sky-f...

Takes too much clicking...

How do I bulk follow people?