SmartChoices: Augmenting Software with Learned Implementations

NeurIPS 2023 Workshop MLSys Submission11 Authors

Published: 28 Oct 2023, Last Modified: 12 Dec 2023MlSys Workshop NeurIPS 2023 PosterEveryoneRevisionsBibTeX
Keywords: machine learning, best practices, software development process management, MLOps, contextual bandits, multimetric optimization
TL;DR: We demonstrate how machine learning can be incorporated into software easily, safely and effectively, with a single infrastructure product powering a wide range of systems applications.
Abstract: We are living in a golden age of machine learning. Powerful models perform many tasks far better than is possible using traditional software engineering approaches alone. However, developing and deploying these models in existing software systems remains challenging. In this paper, we present SmartChoices, a novel approach to incorporating machine learning into mature software stacks easily, safely, and effectively. We highlight key design decisions and present case studies applying SmartChoices within a range of large-scale industrial systems.
Submission Number: 11