Microsoft Technology Licensing, LLC

Vijay Kumar Ramani

Marc Todd Friedman

Alekh Jindal

Hiren Shantilal Patel

Shi Qiao

Markus Weimer

Irene Rogan Shaffer

Lucas Rosenblatt

Abhishek Roy

Gilbert Antonius

Remmelt Herbert Lieve Ammerlaan

H M Sajjad Hossain

Peter Orenberg

Soundararajan Srinivasan

Methods of machine learning for system deployments without performance regressions are performed by systems and devices. A performance safeguard system is used to design pre-production experiments for determining the production readiness of learned models based on a pre-production budget by leveraging big data processing infrastructure and deploying a large set of learned or optimized models for its query optimizer. A pipeline for learning and training differentiates the impact of query plans with and without the learned or optimized models, selects plan differences that are likely to lead to most dramatic performance difference, runs a constrained set of pre-production experiments to empirically observe the runtime performance, and finally picks the models that are expected to lead to consistently improved performance for deployment. The performance safeguard system enables safe deployment not just for learned or optimized models but also for additional of other ML-for-Systems features.

System and method for machine learning for system deployments without performance regressions

Growing community of inventors

Boston, MA, United States of America

Vijay Kumar Ramani