This cluster will convene an interdisciplinary group of scholars to develop firm theoretical and philosophical foundations for addressing some major issues concerning interpretability of machine learning based models. Program participants include experts in theoretical computer science, machine learning, statistics, causal inference, fairness and the present community on interpretability. We aim to address the following fundamental questions about how to best use machine learning for real-life tasks:
- What notions of intepretability might render models that are more amenable to monitoring by regulators?
- How can the quality and usefulness of interpretation in a given context (such as a particular human audience, and for a particular domain problem) be evaluated both empirically and theoretically?
- For which of the desiderata that interpretability purports to address must we sacrifice predictive accuracy?
- Are there any feasibly measurable properties of neural networks that can yield significant insights into their input-output functionality? More generally, are there sound theoretical principles under which today’s deep learning tools can be leveraged to confer insights beyond their predictive accuracy?
- What role, if any, do various interpretation or explanation techniques have to offer the discourse on algorithmic fairness and discrimination? Are there any inherent tradeoffs between notions of interpretability and fairness?
The cluster will address a variety of perspectives on defining and developing tools for achieving these goals in automated decision-making systems.
sympa [at] lists [dot] simons [dot] berkeley [dot] edu (body: subscribe%20iml2020announcements%40lists.simons.berkeley.edu) (Click here to subscribe to our announcements email list for this program).
Shai Ben David (University of Waterloo; chair), Zachari Lipton (Carnegie Mellon University), Ruth Urner (York University) and Bin Yu (UC Berkeley)
Long-Term Participants (including Organizers):
Shai Ben-David (University of Waterloo), Simina Branzei (Purdue University), Rich Caruana (Microsoft Research), Sanjoy Dasgupta (University of California), Karolina Dziugaite (Element AI), Alexandra Korolova (University of Southern California), Zachari Lipton (Carnegie Mellon University), Nati Srebro (Toyota Technological Institute), Ruth Urner (York University), Bin Yu (UC Berkeley)
Those interested in participating in this program should send an email to the organizers at this iml2020 [at] lists [dot] simons [dot] berkeley [dot] edu (at this address).