Optimization on black-box function by parameter-shift rule
This addresses optimization challenges in machine learning training for models with complex, untraceable relationships, though it appears incremental as it adapts an existing quantum method to this domain.
The paper tackles the problem of optimizing black-box functions with uncertain parameter-outcome relationships by proposing a zeroth-order method based on the parameter-shift rule from quantum computing, which uses fewer parameters than previous methods.
Machine learning has been widely applied in many aspects, but training a machine learning model is increasingly difficult. There are more optimization problems named "black-box" where the relationship between model parameters and outcomes is uncertain or complex to trace. Currently, optimizing black-box models that need a large number of query observations and parameters becomes difficult. To overcome the drawbacks of the existing algorithms, in this study, we propose a zeroth-order method that originally came from quantum computing called the parameter-shift rule, which has used a lesser number of parameters than previous methods.