final-year Princeton CS PhD student / Graduated from Yao Class, Tsinghua University / OIer
Highlights
- Pro
Popular repositories Loading
-
grokking-dichotomy
grokking-dichotomy PublicCode for "Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking"
-
max-margin
max-margin PublicCode for the paper "Gradient Descent Maximizes the Margin of Homogeneous Neural Networks"
Python 8
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.