Proceedings of the VLDB Endowment · 2019 · 48 citations · 61 references
ComputingComputer ScienceAlgorithmsFeature EngineeringMachine LearningData PipelinesData PreprocessingData-flow AnalysisOptimization For Machine LearningRepresentation LearningDense Linear AlgebraDomain-specific Language DesignHigh-level Intermediate RepresentationIntermediate Representation DesignMonadsPipeline OptimizationTrainingUser-defined Functions
Machine learning (ML) pipelines for model training and validation typically include preprocessing, such as data cleaning and feature engineering, prior to training an ML model. Preprocessing combines relational algebra and user-defined functions (UDFs), while model training uses iterations and linear algebra. Current systems are tailored to either of the two. As a consequence, preprocessing and ML steps are optimized in isolation. To enable holistic optimization of ML training pipelines, we present Lara, a declarative domain-specific language for collections and matrices. Lara's inter-mediate representation (IR) reflects on the complete program, i.e., UDFs, control flow, and both data types. Two views on the IR enable diverse optimizations. Monads enable operator pushdown and fusion across type and loop boundaries. Combinators provide the semantics of domain-specific operators and optimize data access and cross-validation of ML algorithms. Our experiments on preprocessing pipelines and selected ML algorithms show the effects of our proposed optimizations on dense and sparse data, which achieve speedups of up to an order of magnitude.
61
Scikit-learn: Machine Learning in Python
Fabián Pedregosa, Gaël Varoquaux, Alexandre Gramfort et al. · arXiv (Cornell University) · 2012 · 63.7K citations · Full text
A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection
Ron Kohavi · 1995 · 10.7K citations · Full text
Scikit-learn: Machine Learning in Python
PedregosaFabian, VaroquauxGaël, GramfortAlexandre et al. · Journal of Machine Learning Research · 2011 · 8.2K citations
TensorFlow: a system for large-scale machine learning
Martı́n Abadi, Paul Barham, Jianmin Chen et al. · Operating Systems Design and Implementation · 2016 · 6.4K citations
Spark: cluster computing with working sets
Matei Zaharia, Mosharaf Chowdhury, Michael J. Franklin et al. · 2010 · 4.2K citations