Skip to yearly menu bar Skip to main content


Applied Online Algorithms with Heterogeneous Predictors

Jessica Maghakian · Russell Lee · Mohammad Hajiesmaili · Jian Li · Ramesh Sitaraman · Zhenhua Liu

Exhibit Hall 1 #124
[ ]
[ Slides [ PDF [ Poster


For many application domains, the integration of machine learning (ML) models into decision making is hindered by the poor explainability and theoretical guarantees of black box models. Although the emerging area of algorithms with predictions offers a way to leverage ML while enjoying worst-case guarantees, existing work usually assumes access to only one predictor. We demonstrate how to more effectively utilize historical datasets and application domain knowledge by intentionally using predictors of different quantities. By leveraging the heterogeneity in our predictors, we are able to achieve improved performance, explainability and computational efficiency over predictor-agnostic methods. Theoretical results are supplemented by large-scale empirical evaluations with production data demonstrating the success of our methods on optimization problems occurring in large distributed computing systems.

Chat is not available.