Uncovering the Hidden Cost of Model Compression

D Misra, M Chaudhary, A Goyal… - Proceedings of the …, 2024 - openaccess.thecvf.com
In an age dominated by resource-intensive foundation models the ability to efficiently adapt
to downstream tasks is crucial. Visual Prompting (VP) drawing inspiration from the prompting …

On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks

WT Redman, Z Wang, A Ingrosso, S Goldt - arxiv preprint arxiv …, 2024 - arxiv.org
Since its use in the Lottery Ticket Hypothesis, iterative magnitude pruning (IMP) has become
a popular method for extracting sparse subnetworks that can be trained to high performance …