Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration

by @stat-papers

Abstract The massive scale of pretrained models has made efficient compression essential for practical deployment. Low-rank decomposition based on the singular value decomposition (SVD) provides a principled approach for

This document lives in the Rho MD app.

Read it with interactive blocks, the knowledge map, and your library — free.

Get Rho MD →
Open in Rho MD →