US 12,033,036 B2
Systems and methods for implementing an intelligent tuning of multiple hyperparameter criteria of a model constrained with metric thresholds
Michael McCourt, San Francisco, CA (US); Bolong Cheng, San Francisco, CA (US); Taylor Jackie Spriggs, San Francisco, CA (US); Halley Vance, San Francisco, CA (US); Olivia Kim, San Francisco, CA (US); Ben Hsu, San Francisco, CA (US); Sarth Frey, San Francisco, CA (US); Patrick Hayes, San Francisco, CA (US); and Scott Clark, San Francisco, CA (US)
Assigned to Intel Corporation, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Jul. 30, 2020, as Appl. No. 16/943,643.
Claims priority of provisional application 62/880,895, filed on Jul. 31, 2019.
Prior Publication US 2021/0034924 A1, Feb. 4, 2021
Int. Cl. G06N 20/00 (2019.01); G06F 9/54 (2006.01); G06F 18/2115 (2023.01); G06F 18/214 (2023.01); G06N 20/20 (2019.01)
CPC G06N 20/00 (2019.01) [G06F 9/541 (2013.01); G06F 18/2115 (2023.01); G06F 18/2148 (2023.01); G06N 20/20 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method to tune hyperparameters of a machine learning model, the method comprising:
defining a joint tuning function that is based on a combination of a first objective function and a second objective function, the first objective function and the second objective function from a multi-criteria tuning request to tune the hyperparameters of the machine learning model;
identifying a Pareto efficient frontier curve based on the joint tuning function;
demarcating the Pareto efficient frontier curve, based on one or more thresholds, into a first section that is available to search and a second section that is unavailable to search; and
identifying, by configuring a machine, hyperparameter values from the first section of the Pareto efficient frontier curve based on the first section being available to search without causing the machine to search the second section that is demarcated as unavailable to search.