Systems and methods for implementing an intelligent application program interface for an intelligent optimization platform
Systems and methods for implementing an application programming interface (API) that controls operations of a machine learning tuning service for tuning a machine learning model for improved accuracy and computational performance includes an API that is in control communication the tuning service that: executes a first API call function that includes an optimization work request that sets tuning parameters for tuning hyperparameters of a machine learning model; and initializes an operation of distinct tuning worker instances of the service that each execute distinct tuning tasks for tuning the hyperparameters; executes a second API call function that identifies raw values for the hyperparameters; and generates suggestions comprising proposed hyperparameter values selected from the plurality of raw values for each of the hyperparameters; and executes a third API call function that returns performance metrics relating to a real-world performance of the subscriber machine learning model executed with the proposed hyperparameter values.
1. An apparatus comprising: at least one memory; instructions in the apparatus; and processor circuitry to execute the instructions to: access a tuning work request, the tuning work request including hyperparameter ranges and hyperparameters to tune in a model; and execute at least one application programming interface (API) to: initialize a plurality of tuning worker instances to run a plurality of tuning tasks to tune the hyperparameters of the model; and select hyperparameter values for the tuning worker instances based on the running of the plurality of tuning tasks to tune the hyperparameters of the model.
2. The apparatus of claim 1 , wherein the processor circuitry is to execute the instructions to execute the at least one API to initialize the plurality of the tuning worker instances in response to a first API call.
3. The apparatus of claim 2 , wherein the processor circuitry is to execute the instructions to execute the at least one API to select the hyperparameter values in response to a second API call.
4. The apparatus of claim 1 , wherein the processor circuitry is to execute the instructions to execute the at least one API to create an observation object including observation data, the observation date including a measured value of a metric of the model.
5. The apparatus of claim 1 , wherein the model is implemented using a Bayesian method.
6. The apparatus of claim 1 , wherein the model is implemented using a random forest.
7. The apparatus of claim 1 , wherein the processor circuitry is to execute the instructions to execute the tuning work request in parallel with at least a second tuning work request.
8. A computer-readable storage device or storage disk comprising instructions that, when executed, cause processor circuitry to at least:
access a tuning work request, the tuning work request including hyperparameter ranges and hyperparameters to tune in a model; and
execute at least one application programming interface (API) to:
initialize a plurality of tuning worker instances to run a plurality of tuning tasks to tune the hyperparameters of the model; and
select hyperparameter values for the tuning worker instances based on the running of the plurality of tuning tasks to tune the hyperparameters of the model.
9. The computer-readable storage device or storage disk of claim 8 , wherein the instructions are to cause the processor circuitry to execute the at least one API to initialize the plurality of the tuning worker instances in response to a first API call.
10. The computer-readable storage device or storage disk of claim 9 , wherein the instructions are to cause the processor circuitry to execute the at least one API to select the hyperparameter values in response to a second API call.
11. The computer-readable storage device or storage disk of claim 8 , wherein the instructions are to cause the processor circuitry to execute the at least one API to create an observation object including observation data, the observation date including a measured value of a metric of the model.
12. The computer-readable storage device or storage disk of claim 8 , wherein the model is implemented using a Bayesian method.
13. The computer-readable storage device or storage disk of claim 8 , wherein the model is implemented using a random forest.
14. The computer-readable storage device or storage disk of claim 8 , wherein the instructions are to cause the processor circuitry to execute the instructions to execute the tuning work request in parallel with at least a second tuning work request.
15. A method comprising:
accessing a tuning work request by executing an instruction with processor circuitry, the tuning work request including hyperparameter ranges and hyperparameters to tune in a model; and
executing, by executing an instruction with the processor circuitry, at least one application programming interface (API) to:
initialize a plurality of tuning worker instances to run a plurality of tuning tasks to tune the hyperparameters of the model; and
select hyperparameter values for the tuning worker instances based on the running of the plurality of tuning tasks to tune the hyperparameters of the model.
16. The method of claim 15 , wherein the executing of the at least one API is to initialize the plurality of the tuning worker instances in response to a first API call.
17. The method of claim 16 , wherein the executing of the at least one API is to select the hyperparameter values in response to a second API call.
18. The method of claim 15 , wherein the executing of the at least one API is to create an observation object including observation data, the observation date including a measured value of a metric of the model.
19. The method of claim 15 , wherein the model is implemented using a Bayesian method.
20. The method of claim 15 , wherein the model is implemented using a random forest.
21. The method of claim 15 , further including executing the tuning work request in parallel with at least a second tuning work request.