Replica Method for the Machine Learning Theorist

Check out these blog posts part one and part two as well as the Tex writeup. These were authored by me, Haozhe Shan, Boaz Barak, Abdul Canatar, Cengiz Pehlevan.

Kernel Regression Generalization: Spectral Bias and Multiple Descents

This colab notebook contains an introduction to an average case analysis of generalization in kernel regression, exploring spectral bias and the non-monotonicity of the risk curves in the presence of noise.