[Theory] REMINDER: 3/31 Talks at TTIC: Juba Ziani, Georgia Institute of Technology

[Mary Marre]

*When:*        Friday, March 31, 2023 at* 2:30 pm** CT   *


*Where:       *Talk will be given *live, in-person* at

                   TTIC, 6045 S. Kenwood Avenue

                   5th Floor, Room 530


*Virtually:*  *via* Panopto (*livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=5aa81108-ea99-4e34-806a-afd00002109e>*
)


*Who:          *Juba Ziani, Georgia Institute of Technology
------------------------------
*Title:*          Information Discrepancy in Strategic Learning

*Abstract:* We study 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.

*Bio: *Juba Ziani is an Assistant Professor in the H. Milton Stewart School
of Industrial and Systems Engineering. Prior to this, Juba was a Warren
Center Postdoctoral Fellow at the University of Pennsylvania, hosted by
Sampath Kannan, Michael Kearns, Aaron Roth, and Rakesh Vohra. Juba
completed his PhD at Caltech in the Computing and Mathematical Sciences
department, where he was advised by Katrina Ligett and Adam Wierman. Juba
studies the optimization, game theoretic, economic, ethical, and societal
challenges that arise from transactions and interactions involving data. In
particular, his research focuses on the design of markets for data, on data
privacy with a focus on "differential privacy", on fairness in machine
learning and decision-making, and on strategic considerations in machine
learning.

*Host: *Ali Vakilian <vakilian at ttic.edu>



Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue, Rm 517*
*Chicago, IL  60637*
*773-834-1757*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Sat, Mar 25, 2023 at 1:52 PM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*        Friday, March 31, 2023 at* 2:30 pm** CT   *
>
>
> *Where:       *Talk will be given *live, in-person* at
>
>                    TTIC, 6045 S. Kenwood Avenue
>
>                    5th Floor, Room 530
>
>
> *Virtually:*  *via* Panopto (*livestream
> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=5aa81108-ea99-4e34-806a-afd00002109e>*
> )
>
>
> *Who:          *Juba Ziani, Georgia Institute of Technology
> ------------------------------
> *Title:*          Information Discrepancy in Strategic Learning
>
> *Abstract:* We study 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.
>
> *Bio: *Juba Ziani is an Assistant Professor in the H. Milton Stewart
> School of Industrial and Systems Engineering. Prior to this, Juba was a
> Warren Center Postdoctoral Fellow at the University of Pennsylvania, hosted
> by Sampath Kannan, Michael Kearns, Aaron Roth, and Rakesh Vohra. Juba
> completed his PhD at Caltech in the Computing and Mathematical Sciences
> department, where he was advised by Katrina Ligett and Adam Wierman. Juba
> studies the optimization, game theoretic, economic, ethical, and societal
> challenges that arise from transactions and interactions involving data. In
> particular, his research focuses on the design of markets for data, on data
> privacy with a focus on "differential privacy", on fairness in machine
> learning and decision-making, and on strategic considerations in machine
> learning.
>
> *Host: *Ali Vakilian <vakilian at ttic.edu>
>
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue, Rm 517*
> *Chicago, IL  60637*
> *773-834-1757*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20230330/2b8c7277/attachment-0001.html>