Genesis: a language for generating synthetic training programs for machine learning

Abstract

We describe Genesis, a language for the generation of synthetic programs for use in machine learning-based performance auto-tuning. The language allows users to annotate a template program to customize its code using statistical distributions and to generate program instances based on those distributions. This effectively allows users to generate training programs whose characteristics or features vary in a statistically controlled fashion. We describe the language constructs, a prototype preprocessor for the language, and three case studies that show the ability of Genesis to express a range of training programs in different domains. We evaluate the preprocessor's performance and the statistical quality of the samples it generates. We believe that Genesis is a useful tool for generating large and diverse sets of programs, a necessary component when training machine learning models for auto-tuning.