🐈‍⬛️ Learning Theory Circle — Session 1

We're starting a biweekly reading group on the theory of deep learning. Every other Sunday, one person presents one paper — their own work or someone else's — followed by open discussion.

🗓 Sunday, Aug 2 · 7:00 PM (Tehran, UTC+3:30)

🎤 Erfan Sobhaei — Sharif University of Technology

📄 "A Modern Take on the Bias–Variance Tradeoff in Neural Networks"

Why start here: the textbook bias–variance tradeoff says bigger models should overfit. Modern neural networks don't seem to get the memo — variance can actually shrink as width grows. This paper takes that puzzle apart, which makes it a fitting first session for a theory group.

📍 Live on Google Meet

🔗 Schedule, links & past talks: learning-theory-circle.github.io

Want to present a future session? Get in touch or open a PR on the site. See you Sunday!

#learning_theory
@SingularThinker