all AI news
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks. (arXiv:2206.01278v1 [cs.LG])
June 6, 2022, 1:11 a.m. | Mansheej Paul, Brett W. Larsen, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite
stat.ML updates on arXiv.org arxiv.org
A striking observation about iterative magnitude pruning (IMP; Frankle et al.
2020) is that $\unicode{x2014}$ after just a few hundred steps of dense
training $\unicode{x2014}$ the method can find a sparse sub-network that can be
trained to the same accuracy as the dense network. However, the same does not
hold at step 0, i.e. random initialization. In this work, we seek to understand
how this early phase of pre-training leads to a good initialization for IMP
both through the lens …
More from arxiv.org / stat.ML updates on arXiv.org
Entropic covariance models
3 days, 12 hours ago |
arxiv.org
Uncertainty quantification in metric spaces
3 days, 12 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York