Accelerating Machine Learning Inference with Probabilistic Predicates
SIGMOD/PODS '18: International Conference on Management of Data Houston TX USA June, 2018, pp. 1493-1508, 2018.
Classic query optimization techniques, including predicate pushdown, are of limited use for machine learning inference queries, because the user-defined functions (UDFs) which extract relational columns from unstructured inputs are often very expensive; query predicates will remain stuck behind these UDFs if they happen to require relatio...More
Full Text (Upload PDF)
PPT (Upload PPT)