Declarative Recursive Computation on an RDBMS, or, Why You Should Use a Database For Distributed Machine Learning
This work addresses the challenge of scaling machine learning for large models and datasets, offering a novel approach that leverages existing database infrastructure, though it appears incremental in its modifications.
The authors tackled the problem of distributed machine learning by proposing minimal modifications to a relational database management system (RDBMS) to support such computations, resulting in a system that enables trivial scaling to large datasets and models that exceed RAM capacity.
A number of popular systems, most notably Google's TensorFlow, have been implemented from the ground up to support machine learning tasks. We consider how to make a very small set of changes to a modern relational database management system (RDBMS) to make it suitable for distributed learning computations. Changes include adding better support for recursion, and optimization and execution of very large compute plans. We also show that there are key advantages to using an RDBMS as a machine learning platform. In particular, learning based on a database management system allows for trivial scaling to large data sets and especially large models, where different computational units operate on different parts of a model that may be too large to fit into RAM.