Distributed Processing for Machine Learning Production Pipelines Altay, Crowe, Rokni

Speakers: Ahmet Altay, Robert Crowe, Reza Rokni Production ML workloads often require very large compute and system resources, which leads to the application of distributed processing on clusters. On premises or cloudbased infrastructure cost requires maximum efficient use of resources. This makes distributed processing pipeline frameworks such as Apache Flink ideal for ML workloads. In addition, production ML must address issues of modern software methodology, as well as issues unique to ML. Different ty