@InProceedings{2020:ICDS:Lynceus,
      AUTHOR = {Casimiro, Maria and Didona, Diego and Romano, Paolo and Rodrigues, Luis and Zwaenepoel, Willy and Garlan, David},
      TITLE = {Lynceus: Cost-efficient Tuning and Provisioning of Data Analytic Jobs},
      YEAR = {2020},
      MONTH = {8-10 July},
      BOOKTITLE = {The 40th International Conference on Distributed Computing Systems},
      ADDRESS = {Singapore},
      PDF = {http://acme.able.cs.cmu.edu/pubs/uploads/pdf/ICDCS_2020_paper_2972020_ICDS_Lynceus.pdf},
      ABSTRACT = {Modern data analytic and machine learning jobs find in the cloud a natural deployment platform to satisfy their notoriously large resource requirements. Yet, to achieve cost efficiency, it is crucial to identify a deployment configuration that satisfies user-defined QoS constraints (e.g., on execution time), while avoiding unnecessary over-provisioning. This paper introduces Lynceus, a new approach for the optimization of cloud-based data analytic jobs that improves over state-of-the-art approaches by enabling significant cost savings both in terms of the final recommended configuration and of the optimization process used to recommend configurations. Unlike existing solutions, Lynceus optimizes in a joint fashion both the cloud-related (i.e., which and how many machines to provision) and the application-level (e.g. the hyper-parameters of a machine learning algorithm) parameters. This allows for a reduction of the cost of recommended configurations by up to 3.7X at the 90-th percentile with respect to existing approaches, which treat the optimization of cloud-related and application level parameters as two independent problems. Further, Lynceus reduces the cost of the optimization process (i.e., the cloud cost incurred for testing configurations) by up to 11X. Such an improvement is achieved thanks to two mechanisms: i) a timeout approach which allows to abort the exploration of configurations that are deemed suboptimal, while still extracting useful information to guide future explorations and to improve its predictive model — differently from recent works, which either incur the full cost for testing suboptimal configurations or are unable to extract any knowledge from aborted runs; ii) a long-sighted and budget-aware technique that determines which configurations to test by predicting the long-term impact of each exploration — unlike state-of-the-art approaches for the optimization of cloud jobs, which adopt greedy optimization methods.},
      KEYWORDS = {Big data, Machine Learning, Resource Allocation}
}