A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks
[article]
2022
arXiv
pre-print
Preserved Fulltext
network correlates well with good initializations for IMP. ...
We additionally observe that by pre-training only on "easy" training data, we can decrease the number of steps necessary to find a good initialization for IMP compared to training on the full dataset or ...
Roy for feedback on multiple drafts. ...
arXiv:2206.01278v1
fatcat:v2miqupbavbrharhw2qtkh7uam