Nvidia Corporation

Saurav Muralidharan

Michael Garland

Animesh Garg

Vinu Joseph

One embodiment of a method includes determining, by a Bayesian optimizer, a first sparsity ratio associated with a limit on an accuracy loss caused by compressing the machine learning model. The method further includes selecting, by the Bayesian optimizer, a second sparsity ratio that optimizes a predefined objective function for the machine learning model within a search space bounded by the first sparsity ratio. The method further includes generating a compressed version of the machine learning model having the second sparsity ratio.

Growing community of inventors

San Jose, CA, United States of America

Saurav Muralidharan