Bayesian optimization of sparsity ratios in model compression

A non-transitory computer readable medium storing instructions that, when executed by a processor, cause the processor to compress a machine learning model by performing the steps of:

• determining, by a Bayesian optimizer, a first sparsity ratio associated with a limit on an accuracy loss caused by compressing the machine learning model;
• 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;
• and
• generating a compressed version of the machine learning model having the second sparsity ratio.

A system, comprising:

• a memory storing instructions;
• and
• a processor for executing the instructions to:
• determine, by a Bayesian optimizer, a first sparsity ratio associated with a limit on an accuracy loss caused by compressing the machine learning model;
• select, 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;
• and
• generate a compressed version of the machine learning model having the second sparsity ratio.