Optimization of Parameters of a System, Product, or Process

Abstract

The present disclosure provides computing systems and associated methods for optimizing one or more adjustable parameters (e.g. operating parameters) of a system. In particular, the present disclosure provides a parameter optimization system that can perform one or more black-box optimization techniques to iteratively suggest new sets of parameter values for evaluation. The iterative suggestion and evaluation process can serve to optimize or otherwise improve the overall performance of the system, as evaluated by an objective function that evaluates one or more metrics. The present disclosure also provides a novel black-box optimization technique known as “Gradientless Descent” that is more clever and faster than random search yet retains most of random search's favorable qualities.

1 .- 21 . (canceled) 
     
     
         22 . A computer-implemented method for use in optimization of parameters of a system, product, or process, the method comprising:
 establishing, by one or more computing devices, an optimization procedure for a system, product, or process, wherein the system, product, or process has an evaluable performance that is dependent on values of one or more adjustable parameters;   receiving, by the one or more computing devices, one or more prior evaluations of performance of the system, product, or process, the one or more prior evaluations being respectively associated with one or more prior variants of the system, product, or process, the one or more prior variants each being defined by a set of values for the one or more adjustable parameters;   utilizing, by the one or more computing devices, an optimization algorithm to generate a suggested variant based at least in part on the one or more prior evaluations of performance and the associated set of values, the suggested variant being defined by a suggested set of values for the one or more adjustable parameters; and   performing, by the one or more computing devices, transfer learning to obtain initial values for the one or more adjustable parameters based on the one or more prior variants.   
     
     
         23 . The computer-implemented method of  claim 22 , wherein the one or more prior variants comprise a plurality of prior optimization procedures. 
     
     
         24 . The computer-implemented method of  claim 23  wherein performing, by the one or more computing devices, transfer learning comprises:
 identifying, by the one or more computing devices, the plurality of prior optimization procedures, wherein the plurality of prior optimization procedures are organized in a sequence; and 
 building, by the one or more computing devices, a plurality of Gaussian Process regressors respectively for the plurality of prior optimization procedures. 
 
     
     
         25 . The computer-implemented method of  claim 24 , wherein the Gaussian Process regressor for each prior optimization procedure is trained on one or more residuals relative to the Gaussian Process regressor for a previous prior optimization procedure in the sequence. 
     
     
         26 . The computer-implemented method of  claim 24 , wherein the sequence is in temporal order based on when the plurality of prior optimization procedures were performed. 
     
     
         27 . A computer system operable to suggest trial parameters, the computer system comprising:
 a database that stores one or more results respectively associated with one or more trials of a study, the one or more trials for the study respectively comprising one or more sets of values for one or more adjustable parameters associated with the study, the result for each trial comprising an evaluation of the corresponding set of values for the one or more adjustable parameters;   one or more processors; and   one or more non-transitory computer-readable media that store instructions that, when executed by the one or more processors, cause the computer system to perform operations, the operations comprising:
 performing one or more black-box optimization techniques to generate a suggested trial based at least in part on the one or more results and the one or more sets of values respectively associated with the one or more results, the suggested trial including a suggested set of values for the one or more adjustable parameters; and 
 performing transfer learning to obtain initial values for the one or more adjustable parameters. 
   
     
     
         28 . The computer system of  claim 27 , wherein the operations further comprise:
 accepting an adjustment to the suggested trial from a user, the adjustment comprising at least one change to the suggested set of values to form an adjusted set of values;   receiving a new result obtained through evaluation of the adjusted set of values; and   associating the new result and the adjusted set of values with the study in the database.   
     
     
         29 . The computer system of  claim 28 , wherein the operations further comprise:
 generating a second suggested trial based at least in part on the new result for the adjusted set of values, the second suggested trial including a second suggested set of values for the one or more adjustable parameters.   
     
     
         30 . The computer system of  claim 27 , wherein performing transfer learning comprises:
 identifying a plurality of studies, the plurality of studies organized in a sequence; and   building a plurality of Gaussian Process regressors respectively for the plurality of studies, wherein the Gaussian Process regressor for each study is trained on one or more residuals relative to the Gaussian Process regressor for a previous study in the sequence.   
     
     
         31 . The computer system of  claim 30 , wherein the sequence is in temporal order based on when the plurality of studies were performed. 
     
     
         32 . The computer system of  claim 27 , wherein the operations further: comprise performing a plurality of rounds of generation of suggested trials using at least two different black-box optimization techniques. 
     
     
         33 . The computer system of  claim 32 , wherein the operations further comprise automatically and dynamically changing black-box optimization techniques between at least two of the plurality of rounds of generation of suggested trials. 
     
     
         34 . The computer system of  claim 27 , wherein the one or more black-box optimization techniques are stateless so as to enable switching between black-box optimization techniques during the study. 
     
     
         35 . The computer system of  claim 27 , wherein the operations further comprise:
 performing a plurality of rounds of generation of suggested trials; and   receiving a change to a feasible set of values for at least one of the one or more adjustable parameters between at least two of the plurality of rounds of generation of suggested trials.   
     
     
         36 . The computer system of  claim 27 , wherein the operations further comprise:
 receiving a plurality of requests for additional suggested trials for the study;   batching at least a portion of the plurality of requests together; and   generating, as a batch, the additional suggested trials in response to the plurality of requests.   
     
     
         37 . The computer system of  claim 27 , wherein the operations further comprise providing for display a parallel coordinates visualization of the one or more results and the one or more sets of values for the one or more adjustable parameters. 
     
     
         38 . A computer-implemented method to suggest trial parameters, the method comprising:
 establishing, by one or more computing devices, a study that comprises one or more adjustable parameters;   receiving, by the one or more computing devices, one or more results respectively associated with one or more trials of the study, the one or more trials respectively comprising one or more sets of values for the one or more adjustable parameters, the result for each trial comprising an evaluation of the corresponding set of values for the one or more adjustable parameters;   generating, by the one or more computing devices, a suggested trial based at least in part on the one or more results and the one or more sets of values, the suggested trial including a suggested set of values for the one or more adjustable parameters; and   performing transfer learning to obtain initial values for the one or more adjustable parameters.   
     
     
         39 . The computer-implemented method of  claim 38 , further comprising:
 receiving, by the one or more computing devices, an adjustment to the suggested trial from a user, the adjustment comprising at least one change to the suggested set of values to form an adjusted set of values;   receiving, by the one or more computing devices, a new result associated with the adjusted set of values; and   associating, by the one or more computing devices, the new result and the adjusted set of values with the study.   
     
     
         40 . The computer-implemented method of  claim 39 , further comprising:
 generating, by the one or more computing devices, a second suggested trial based at least in part on the new result for the adjusted set of values, the second suggested trial including a second suggested set of values for the one or more adjustable parameters.   
     
     
         41 . The computer-implemented method of  claim 39 , wherein generating, by the one or more computing devices, the suggested trial based at least in part on the one or more results and the one or more sets of values comprises:
 requesting, by the one or more computing devices via an internal abstract policy, generation of the suggested trial by an external custom policy provided by the user; and receiving, by the one or more computing devices, the suggested trial from the external custom policy provided by the user.