J
Jonathan Frankle
Researcher at Massachusetts Institute of Technology
Publications - 51
Citations - 5245
Jonathan Frankle is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Pruning (decision trees) & Computer science. The author has an hindex of 19, co-authored 36 publications receiving 3062 citations. Previous affiliations of Jonathan Frankle include Princeton University.
Papers
More filters
Proceedings Article
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks.
Jonathan Frankle,Michael Carbin +1 more
TL;DR: This work finds that dense, randomly-initialized, feed-forward networks contain subnetworks ("winning tickets") that - when trained in isolation - reach test accuracy comparable to the original network in a similar number of iterations, and articulate the "lottery ticket hypothesis".
Posted Content
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Jonathan Frankle,Michael Carbin +1 more
TL;DR: In this paper, the lottery tickets hypothesis is proposed to find the subnetworks that can reach test accuracy comparable to the original network in a similar number of iterations, where the winning tickets have won the initialization lottery: their connections have initial weights that make training particularly effective.
What is the State of Neural Network Pruning
TL;DR: Issues with current practices in pruning are identified, concrete remedies are suggested, and ShrinkBench, an open-source framework to facilitate standardized evaluations of pruning methods are introduced, to be used to compare various pruning techniques.
Proceedings Article
Linear Mode Connectivity and the Lottery Ticket Hypothesis
TL;DR: This work finds that standard vision models become stable to SGD noise in this way early in training, and uses this technique to study iterative magnitude pruning (IMP), the procedure used by work on the lottery ticket hypothesis to identify subnetworks that could have trained in isolation to full accuracy.
Posted Content
The Lottery Ticket Hypothesis: Training Pruned Neural Networks.
Jonathan Frankle,Michael Carbin +1 more
TL;DR: The lottery ticket hypothesis and its connection to pruning are a step toward developing architectures, initializations, and training strategies that make it possible to solve the same problems with much smaller networks.