Timezone: »

 
Poster
Information Discrepancy in Strategic Learning
Yahav Bechavod · Chara Podimata · Steven Wu · Juba Ziani

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #1218
in Poster Session 3 »

We initiate the study of the effects of non-transparency in decision rules on individuals' ability to improve in strategic learning settings. Inspired by real-life settings, such as loan approvals and college admissions, we remove the assumption typically made in the strategic learning literature, that the decision rule is fully known to individuals, and focus instead on settings where it is inaccessible. In their lack of knowledge, individuals try to infer this rule by learning from their peers (e.g., friends and acquaintances who previously applied for a loan), naturally forming groups in the population, each with possibly different type and level of information regarding the decision rule. We show that, in equilibrium, the principal's decision rule optimizing welfare across sub-populations may cause a strong negative externality: the true quality of some of the groups can actually deteriorate. On the positive side, we show that, in many natural cases, optimal improvement can be guaranteed simultaneously for all sub-populations. We further introduce a measure we term information overlap proxy, and demonstrate its usefulness in characterizing the disparity in improvements across sub-populations. Finally, we identify a natural condition under which improvement can be guaranteed for all sub-populations while maintaining high predictive accuracy. We complement our theoretical analysis with experiments on real-world datasets.

Keywords: T: Game Theory · T: Social Aspects · SA: Trustworthy Machine Learning · SA: Accountability, Transparency and Interpretability · SA: Fairness, Equity, Justice and Safety

Author Information

Yahav Bechavod (Hebrew University)
Chara Podimata (Harvard University)

I'm a rising fifth year PhD student in the EconCS group at Harvard University, where I am advised by Professor Yiling Chen. My research interests lie mostly on the intersection of Theoretical Computer Science, Economics, and Machine Learning and specifically on learning under the presence of strategic agents, online learning, and mechanism design. During the summer of 2019 and spring of 2020, I had the pleasure of being an intern at Microsoft Research in New York City, mentored by Jennifer Wortman Vaughan and Alex Slivkins respectively. Before joining Harvard, I was an intern for Google in Athens, Greece. I received my Diploma from the National Technical University of Athens, where I was advised by Professor Dimitris Fotakis.

Steven Wu (Carnegie Mellon University)
Juba Ziani (University of Pennsylvania)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors