REVIEW 2 cited by
FreezeOut: Accelerate Training by Progressively Freezing Layers
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The early layers of a deep neural net have the fewest parameters, but take up the most computation. In this extended abstract, we propose to only train the hidden layers for a set portion of the training run, freezing them out one-by-one and excluding them from the backward pass. Through experiments on CIFAR, we empirically demonstrate that FreezeOut yields savings of up to 20% wall-clock time during training with 3% loss in accuracy for DenseNets, a 20% speedup without loss of accuracy for ResNets, and no improvement for VGG networks. Our code is publicly available at https://github.com/ajbrock/FreezeOut
Forward citations
Cited by 2 Pith papers
-
MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
MoEcho claims to compromise user privacy in MoE LLMs and VLMs via four CPU and GPU side channels, but the provided manuscript body contains no supporting content.
-
PFedDST: Personalized Federated Learning with Decentralized Selection Training
A decentralized personalized federated learning method that scores peers by loss, header similarity, and recency reports faster convergence, but its own CIFAR-100 result contradicts the accuracy claim.
Discussion (0). Continue with ORCID to comment.