Please note this workshop has tentatively been rescheduled for June 28 – July 1, 2021.
Zachari Lipton (Carnegie Mellon University; co-chair), Bin Yu (UC Berkeley; co-chair), Himabindu Lakkaraju (Harvard), David Madigan (Columbia), Deidre Mulligan (UC Berkeley)
This workshop will convene an interdisciplinary group of scholars to inspire clear foundational formulations of interpretability in a variety of domains where questions of interpretability arise in the application of machine learning, statistics, and data science more broadly. The attendees will include scholars from both the natural sciences — including precision medicine and the physical, biological and neuroscience sciences, and the social sciences — including political science, economics, and law, together with machine learners, statisticians, and data scientists. Across these domains, the term "interpretability" is often overloaded to speak to such disparate concerns as assisting in model checking, comparing extracted patterns against domain knowledge, extracting insights and generating hypotheses, anticipating failures on out-of-domain data, and providing accountability and contestability to individuals subject to data-driven decision-making.
Our goal is to collectively characterize both the problems where interpretability concerns arise and the concepts that have arisen in recent efforts to address them. We aim to develop the appropriate theoretical framing of interpretability in the context of these domain problems. In particular, we will discuss and clarify the role of causal inference in various interpretability problems. We will identify desirable theoretical results under these concepts and framing, and discuss steps to test or validate the applicability of these results to the domain problems that motivate us. Where possible, we will propose performance metrics and discuss a workflow for continuously revising our framing to be useful in the intended domain areas for guiding both decision-making and knowledge generation.
Further details about this workshop will be posted in due course. Enquiries may be sent to the organizers workshop-iml1 [at] lists.simons.berkeley.edu (at this address).
Registration is required to attend this workshop. Space may be limited, and you are advised to register early. The link to the registration form will appear on this page approximately 10 weeks before the workshop. To submit your name for consideration, please register and await confirmation of your acceptance before booking your travel.
Shai Ben-David (University of Waterloo), Simina Branzei (Purdue University), Rich Caruana (Microsoft Research), Sanjoy Dasgupta (University of California), Gintare Karolina Dziugaite (Element AI), Alexandra Korolova (University of Southern California), Zachari Lipton (Carnegie Mellon University), Nati Srebro (Toyota Technological Institute), Ruth Urner (York Univesity ), Bin Yu (UC Berkeley), Richard Berk (Penn State), Umang Bhatt (University of Cambridge & Partnership on AI), Alex D'Amour (Google), David Danks (CMU), Heather Gray (UC Berkeley), Joseph Halpern (Cornell University), Kelly Hannah Moffatt (University of Toronto), Tad Hirsch (Northeastern), Shirley Ho (Carnegie Mellon University / Lawrence Berkeley Lab), Anshul Kundaje (Stanford University), Katherine Roeder (CMU), Adrian Weller (University of Cambridge), Rebecca Wexler (UC Berkeley), James Woodward (University of Pittsburgh), Alice Xiang (Partnership on AI)