Systems and methods for implementing an intelligent machine learning optimization platform for multiple tuning criteria

A computer-readable storage device or storage disk comprising instructions to cause programmable circuitry to at least:

• determine a joint function defining a relationship between a first objective function and a second objective function to tune first and second hyperparameters of a model, the joint function to facilitate simultaneous optimization of the first objective function and the second objective function, the first objective function corresponding to a first metric in a multi-criteria optimization work request, the second objective function corresponding to a second metric in the multi-criteria optimization work request, the first metric and the second metric corresponding to a machine learning model;
• change a weight value to increase an emphasis of the first objective function and also decrease an emphasis of the second objective function;
• select a first hyperparameter value for the first hyperparameter and a second hyperparameter value for the second hyperparameter over third and fourth hyperparameter values based on a first performance of the first objective function and a second performance of the second objective function;
• and
• tune the machine learning model based on the first hyperparameter value and the second hyperparameter value.

A method to tune hyperparameters, the method comprising:

• determining, by performing an operation with programmable circuitry, a joint function defining a relationship between a first objective function and a second objective function to tune first and second hyperparameters of a model, the joint function to facilitate simultaneous optimization of the first objective function and the second objective function, the first objective function corresponding to a first metric in a multi-criteria optimization work request, the second objective function corresponding to a second metric in the multi-criteria optimization work request, the first metric and the second metric corresponding to a machine learning model;
• changing, by performing an operation with the programmable circuitry, a tuning value of a tuning factor to increase an emphasis of the first objective function and also decrease an emphasis of the second objective function;
• selecting, by performing an operation with the programmable circuitry, a first hyperparameter value for the first hyperparameter and a second hyperparameter value for the second hyperparameter over third and fourth hyperparameter values based on a first performance of the first objective function and a second performance of the second objective function;
• and
• tuning, by performing an operation with the programmable circuitry, the machine learning model based on the first hyperparameter value and the second hyperparameter value.