# Faster Principal Component Regression and Stable Matrix Chebyshev Approximation

Zeyuan Allen-ZhuYuanzhi Li

We solve principal component regression (PCR), up to a multiplicative accuracy $1+\gamma$, by reducing the problem to $\tilde{O}(\gamma^{-1})$ black-box calls of ridge regression. Therefore, our algorithm does not require any explicit construction of the top principal components, and is suitable for large-scale PCR instances... (read more)

PDF Abstract

No code implementations yet. Submit your code now