CLIMB Evergreen talk with Rina Foygel Barber

Seminar | April 7 | 11 a.m.-12 p.m. | Sutardja Dai Hall, 310 (Banatao Auditorium)

Speaker/Performer:  Prof. Rina Foygel Barber, University of Chicago

Sponsors:  CLIMB Evergreen, FODSI

Stability of black-box algorithms

Algorithmic stability is a framework for studying the properties of a model fitting algorithm, with many downstream implications for generalization, predictive inference, and other important statistical problems. Stability is often defined as the property that predictions on a new test point are not substantially altered by removing a single point at random from the training set. However, this stability property itself is an assumption that may not hold for highly complex predictive algorithms and/or nonsmooth data distributions. This talk will present two complementary views of this problem. In the first part, we show that it is impossible to infer the stability of an algorithm through "black-box testing", where we cannot study the algorithm theoretically but instead try to determine its stability properties by the behavior of the algorithm on various data sets, when data is limited. In the second part, we establish that bagging any black-box algorithm automatically ensures that stability holds, with no assumptions on the algorithm or the data.
This work is joint with Byol Kim, Jake Soloff, and Rebecca Willett.

Bio is here: https://rinafb.github.io/

Target audiences:  Faculty, Students - Graduate, Students - Undergraduate

Open to audience:  All Audiences

Event Contact:  naomiy@berkeley.edu

Access Coordinator:  Naomi Yamasaki,  naomiy@berkeley.edu,  510-710-8488

Webcast:  Webcast