We present AL, a novel automated machine learning system that learns to generate new supervised learning pipelines from an existing corpus of supervised learning programs. In contrast to existing automated machine learning tools, which typically implement a search over manually selected machine learning functions and classes, AL learns to identify the relevant classes in an API by analyzing dynamic program traces that use the target machine learning library. AL constructs a conditional probability model from these traces to estimate the likelihood of the generated supervised learning pipelines and uses this model to guide the search to generate pipelines for new datasets. Our evaluation shows that AL can produce successful pipelines for datasets that previous systems fail to process and produces pipelines with comparable accuracy for datasets that previous systems process successfully.
This program is tentative and subject to change.
Fri 25 Oct
|14:00 - 14:22|
|14:22 - 14:45|
Benjamin MarianoUniversity of Maryland, College Park, Josh ReeseUniversity of Maryland, College Park, Siyuan XuPurdue University, ThanhVu NguyenUniversity of Nebraska, Lincoln, Xiaokang QiuPurdue University, Jeffrey S. FosterTufts University, Armando Solar-LezamaMassachusetts Institute of Technology
|14:45 - 15:07|
|15:07 - 15:30|
Anders MiltnerPrinceton University, Sumit GulwaniMicrosoft, Vu LeMicrosoft, Alan LeungMicrosoft, Arjun RadhakrishnaMicrosoft, Gustavo SoaresMicrosoft, Ashish TiwariMicrosoft, Abhishek UdupaMicrosoftPre-print Media Attached