AWhat changed
Used magnitude pruning followed by resetting surviving weights to their original initialization to identify sparse subnetworks that trained effectively in the tested dense networks.
Scientific scope
Used magnitude pruning followed by resetting surviving weights to their original initialization to identify sparse subnetworks that trained effectively in the tested dense networks. A hypothesis supported by experiments, not a theorem for every network, initialization or dataset.2018v1 tests XOR/MNIST;2019 v5 extends to specifiedCIFAR-10 networks and warmup-sensitive deeper cases. Searching for tickets includes dense training and repeated pruning; sparse final size is not a guaranteed reduction in total discovery cost.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. A hypothesis supported by experiments, not a theorem for every network, initialization or dataset.2018v1 tests XOR/MNIST;2019 v5 extends to specifiedCIFAR-10 networks and warmup-sensitive deeper cases. Searching for tickets includes dense training and repeated pruning; sparse final size is not a guaranteed reduction in total discovery cost.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- The Lottery Ticket Hypothesis: Training Pruned Neural Networks
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction