HCII Seminar Series - Rich Caruana
Senior Principal Researcher at Microsoft Research in Redmond, WA
This presentation will be held virtually. Please join us via the video link below.
"Friends Don’t Let Friends Deploy Black-Box Models: The Importance of Intelligibility in Machine Learning"
In machine learning sometimes tradeoffs must be made between accuracy, privacy and intelligibility: the most accurate models usually are not very intelligible or private, and the most intelligible models usually are less accurate. This can limit the accuracy and privacy of models that can safely be deployed in mission-critical applications such as healthcare where being able to understand, validate, edit, and trust models is important. EBMs (Explainable Boosting Machines) are a recent learning method based on generalized additive models (GAMs) that are as accurate as full complexity models, more intelligible than linear models, and which can be made differentially private with little loss in accuracy. EBMs make it easy to understand what a model has learned and to edit the model when it learns inappropriate things. In the talk I’ll present multiple case studies where EBMs discover surprising patterns in data that would have made deploying black-box models risky. I’ll describe how to train these glassbox models with boosted trees, and with deep neural nets, and I’ll briefly discuss how we’re using these models to uncover and mitigate bias in models where fairness and transparency are important.
Rich Caruana is a senior principal researcher at Microsoft Research. Before joining Microsoft, Rich was on the faculty in the Computer Science Department at Cornell University, at UCLA’s Medical School, and at CMU’s Center for Learning and Discovery. Rich’s Ph.D. is from Carnegie Mellon University, where he worked with Tom Mitchell and Herb Simon. His thesis on Multi-Task Learning helped create interest in a new subfield of machine learning called Transfer Learning. Rich received an NSF CAREER Award in 2004 for Meta Clustering, best paper awards in 2005 (with Alex Niculescu-Mizil), 2007 (with Daria Sorokina), and 2014 (with Todd Kulesza, Saleema Amershi, Danyel Fisher, and Denis Charles), and co-chaired KDD in 2007. His current research focus is on learning for medical decision making, transparent modeling, and deep learning.