activity
20152026
most citedPreconditioned Data Sparsification for Big Data with Applications to PCA and K-means

37 citations · 78 across the 7 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.LG2026

Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration

Farhad Pourkamali-Anaraki

The massive scale of pretrained models has made efficient compression essential for practical deployment. Low-rank decomposition based on the singular value decomposition (SVD) pro…