Loading patent…
AssigneeAmazon Technologies, Inc.
InventorsGilad Amir Rosenberg, John Kyle Brubaker, Martin Schuetz, Helmut Gottfried Katzgraber
Estimating the term…
Methods and apparatus for pruning weights of a trained machine learning model and making pruning adjustments to substantially optimize a loss function. In some embodiments, a machine learning model pruning system is configured to perform a first pruning pass of a machine learning model wherein at least a portion of the weights are set to zero. In some embodiments one or more additional pruning passes of the machine learning model may be performed in batches wherein each batch comprises one or more remaining weights and one or more previously pruned weights. In some embodiments, one or more pruning adjustments may be determined based on an optimization problem that minimizes a loss function for a given batch. In some embodiments, the pruning adjustment comprises restoring a previously pruned weight or pruning a remaining weight of the model.
A system comprising:
A method comprising:
One or more non-transitory computer-readable storage media storing program instructions that, when executed on or across one or more processors, cause the one or more processors to:
Dependencies are inferred from the claim text.