What is recorded here?
Used magnitude pruning followed by resetting surviving weights to their original initialization to identify sparse subnetworks that trained effectively in the tested dense networks.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
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.
Read the original work
- The Lottery Ticket Hypothesis: Training Pruned Neural Networks
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Jonathan Frankle; Michael Carbin
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.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Lottery ticket hypothesis: trainable subnetworks at original initialization
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
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.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Jonathan Frankle; Michael Carbin
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.