LMFAO introduces layered logical and code optimizations for shared computation across batches of aggregates, enabling efficient model learning directly over relational data and outperforming commercial databases and ML libraries by orders of magnitude on four datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Layered Aggregate Engine for Analytics Workloads
LMFAO introduces layered logical and code optimizations for shared computation across batches of aggregates, enabling efficient model learning directly over relational data and outperforming commercial databases and ML libraries by orders of magnitude on four datasets.