Machine learning for databases

Machine learning techniques have been proposed to optimize the databases. For example, traditional empirical database optimization (e.g., cost estimation, join order selection, knob tuning, index and view advisor) cannot meet high-performance requirement for large-scale instances, various applications diversified users, especially on cloud. Fortunately, machine based can alleviate this problem by judiciously selecting strategy. In tutorial, we categorize tasks into three typical problems that be optimized different models, including NP-hard space exploration, index/view partition-key recommendation offline optimization; query rewrite, selection online optimization), regression cost/cardinality benefit latency prediction), prediction workload prediction). We review existing address these provide research challenges.