Skip to yearly menu bar Skip to main content


Poster
in
Workshop: 3rd Workshop on High-dimensional Learning Dynamics (HiLD)

Two-point deterministic equivalence for SGD in random feature models

Alexander Atanasov · Blake Bordelon · Jacob A Zavatone-Veth · Courtney Paquette · Cengiz Pehlevan


Abstract:

We derive a novel deterministic equivalence for the two-point function of a random matrix resolvent. Using this result, we give a unified derivation of the performance of a wide variety of high-dimensional linear models trained with stochastic gradient descent. This includes high-dimensional linear regression, kernel regression, and random feature models. Our results include previously known asymptotics as well as novel ones.

Chat is not available.