Many recent application domains for machine learning deviate from standard modeling assumptions, by including data generated by people who may want to manipulate a system's output, or by trying to accomplish some task for which multiple objectives are simultaneously important. For example, an employer might want to promote their job opportunities to people with certain skills, while simultaneously ensuring a broad range of demographics sees and applies to the job posting. Moreover, if the employer uses a fixed filter to sift out fraudulent applications, the filter will become less useful over time as both fraudulent and honest applicants shift their application contents to pass the filter. In this talk, I will survey some recent results that take steps towards making ML methods more robust to these natural environments often faced in the real world.
Video: To access the live webcast of the talk (active at 16:28 of the day of the presentaton) and the archived version of the talk, use the URL SU-EE380-20190306. This is a first class reference and can be transmitted by email, Twitter, etc.
A URL referencing a YouTube view of the lecture will be posted a week or so following the presentation.
The Stanford EE Computer Systems Colloquium (EE380) meets on Wednesdays 4:30-5:45 throughout the academic year. Talks are given before a live audience in Room 104 of the Shriram Building on the Stanford Campus. The live talks (and the videos hosted at Stanford and on YouTube) are open to the public.
Stanford students may enroll in EE380 to take the Colloquium as a one unit S/NC class. Enrolled students are required to keep and electronic notebook or journal and to write a short, pithy comment about each of the ten lectures and a short free form evaluation of the class in order to receive credit. Assignments are due at the end of the quarter, on the last day of examinations.
EE380 is a video class. Live attendance is encouraged but not required. We (the organizers) feel that watching the video is not a substitute for being present in the classroom. Questions are encouraged.
Many past EE380 talks are available on YouTube, see the EE380 Playlist.
Jamie is an assistant professor in the School of Computer Science Georgia Tech. Prior to this appointment, she was hosted by Michael Kearnsi, Aaron Roth, and Rakesh Vohra as a Warren Center fellow at the University of Pennsylvania. She completed her PhD working with Avrim Blum at Carnegie Mellon University. Her work focuses on the social impact of machine learning and the impact of social behavior on ML's guarantees. How should machine learning be made robust to behavior of the people generating training or test data for it? How should ensure that the models we design do not exacerbate inequalities already present in society?