@misc{hamilton2019mmlspark, author = {Hamilton, Mark and Raghunathan, Sudarshan and Matiach, Ilya and Schonhoffer, Andrew and Raman, Anand and Barzilay, Eli and Rajendran, Karthik and Banda, Dalitso and Hong, Casey Jisoo and Knoertzer, Manon and Brodsky, Ben and Thigpen, Minsoo and Mahajan, Janhavi Suresh and Cochrane, Courtney and Eswaran, Abhiram and Green, Ari}, title = {MMLSpark: Unifying Machine Learning Ecosystems at Massive Scales}, howpublished = {arXiv}, year = {2019}, month = {June}, abstract = {We introduce Microsoft Machine Learning for Apache Spark (MMLSpark), an ecosystem of enhancements that expand the Apache Spark distributed computing library to tackle problems in Deep Learning, Micro-Service Orchestration, Gradient Boosting, Model Interpretability, and other areas of modern computation. Furthermore, we present a novel system called Spark Serving that allows users to run any Apache Spark program as a distributed, sub-millisecond latency web service backed by their existing Spark Cluster. All MMLSpark contributions have the same API to enable simple composition across frameworks and usage across batch, streaming, and RESTful web serving scenarios on static, elastic, or serverless clusters. We showcase MMLSpark by creating a method for deep object detection capable of learning without human labeled data and demonstrate its effectiveness for Snow Leopard conservation.}, url = {http://approjects.co.za/?big=en-us/research/publication/mmlspark-unifying-machine-learning-ecosystems-at-massive-scales/}, }