[Theory] IDEAL - 3/15 Quarterly CS+Econ Workshop: Machine Learning and Strategic Behavior

[Mary Marre]

Upcoming Workshop:
Quarterly CS+Econ Workshop: Machine Learning and Strategic Behavior
*About the Series*

The Quarterly CS+Econ Workshop brings in three or four experts at the
interface between computer science and economics to present their
perspective and research on a common theme. Chicago area researchers with
interest in economics and computer science are invited to attend. The
technical program is in the morning and includes coffee and lunch (on your
own). The afternoon of the workshop will allow for continued discussion
between attendees and the speakers.

The workshop series is organized by Jason Hartline
<https://northwestern.us20.list-manage.com/track/click?u=3fc8e0df393510ea0a5b018e1&id=99fd8e7421&e=01c4c9f9ea>
, Benjamin Golub
<https://northwestern.us20.list-manage.com/track/click?u=3fc8e0df393510ea0a5b018e1&id=40a18bea80&e=01c4c9f9ea>
, Annie Liang
<https://northwestern.us20.list-manage.com/track/click?u=3fc8e0df393510ea0a5b018e1&id=96cc7102e9&e=01c4c9f9ea>
, Marciano Siniscalchi
<https://northwestern.us20.list-manage.com/track/click?u=3fc8e0df393510ea0a5b018e1&id=69b7f2bd27&e=01c4c9f9ea>,
and Alireza Tahbaz-Salehi
<https://northwestern.us20.list-manage.com/track/click?u=3fc8e0df393510ea0a5b018e1&id=1c5d1ad485&e=01c4c9f9ea>.
Funding for the series is provided by the Shaw Family Supporting
Organization CS+X Fund.
*Synopsis*

This edition of this workshop will be on the theme of Machine Learning and
Strategic Behavior. This workshop aims to combine perspectives from
economics and computer science on the topics of: (a) strategic interactions
between agents and machine learning algorithms, and (b) how agents’
decisions might be modeled through the lens of machine learning algorithms.
The speakers are Nika Haghtalab
<https://northwestern.us20.list-manage.com/track/click?u=3fc8e0df393510ea0a5b018e1&id=8655cbf066&e=01c4c9f9ea>
, Jawwad Noor
<https://northwestern.us20.list-manage.com/track/click?u=3fc8e0df393510ea0a5b018e1&id=2f66a07fb9&e=01c4c9f9ea>
, Ran Spiegler
<https://northwestern.us20.list-manage.com/track/click?u=3fc8e0df393510ea0a5b018e1&id=373991c448&e=01c4c9f9ea>,
and Moshe Tenneholtz
<https://northwestern.us20.list-manage.com/track/click?u=3fc8e0df393510ea0a5b018e1&id=fa9aeb0a9c&e=01c4c9f9ea>
.
*Logistics*

   - *Organizers: *Jason Hartline, Benjamin Golub, Annie Liang, Marciano
   Siniscalchi, and Alireza Tahbaz-Salehi
   - *Date: *Monday, March 15, 2021
   - *Location:* Virtual (on Gather.Town and Zoom). Further details to come.
   - *Registration:* Registration
   <https://northwestern.us20.list-manage.com/track/click?u=3fc8e0df393510ea0a5b018e1&id=b644e46fb6&e=01c4c9f9ea>
is
   free but required. Registered participants will be emailed a link by which
   they can virtually attend the workshop.

*Schedule*

   - *11:00-11:30*: Moshe Tenneholtz
   - *11:30-12:00*: Ran Spiegler
   - *12:00-1:00*: Lunch Break and Q&A in GatherTown
   - *1:00-1:30*: Nika Haghtalab
   - *1:30-2:00*: Jawwad Noor
   - *2:00-3:00*: Hangout and Q&A in GatherTown

*Titles and Abstracts*

*Speaker:* Moshe Tenneholtz
*Title:* *Data Science with Game Theory Flavor*
*Abstract: *Design of data science algorithms and techniques, central to
the Internet and on-line media, needs to be revolutionized. Current designs
ignore participants’ strategic incentives. We are establishing an entirely
new repertoire of incentive-compatible data science algorithms and
techniques, with major applications in search and information retrieval,
recommendation systems, regression, on-line learning, clustering and
segmentation, and social networks analysis. In this talk I will briefly
introduce our research agenda, and discuss in more detail a couple of
concrete contributions.

*Speaker:* Ran Spiegler
*Title:* *Cheating with models*
*Abstract: *Beliefs and decisions are often based on confronting models
with data. What is the largest “fake” correlation that a misspecified model
can generate, even when it passes an elementary misspecification test? We
study an “analyst” who fits a model, represented by a directed acyclic
graph, to an objective (multivariate) Gaussian distribution. We
characterize the maximal estimated pairwise correlation for generic
Gaussian objective distributions, subject to the constraint that the
estimated model preserves the marginal distribution of any individual
variable. As the number of model variables grows, the estimated correlation
can become arbitrarily close to one, regardless of the objective
correlation.(joint with Kfir Eliaz and Yair Weiss)
*Speaker:* Nika Haghtalab
*Title:* *Learning and Persuading with Anecdotes*
*Abstract: *This talk presents a model of learning and communication
between two agents using hard anecdotal evidence. We use this model to shed
new light on human communication and justify when and why polarization and
biased belief may arise.
We consider two agents, a sender and a receiver, who have a prior over an
unknown state of the world and must take actions whose payoffs are
determined by their personal preferences as well as the state of the world.
The sender has observed a set of anecdotes, that is a collection of $n$
observations from the state of the world, and can send one these anecdotes
to influence the receiver’s choice of action. We show that if the sender’s
communication scheme is observable by the receiver (that is, the choice of
which anecdote to send given the set of anecdotes), then no matter the
difference in preferences, the agents use an unbiased and maximally
informative communication scheme. Without observability, however, even a
small difference in preferences can lead to significant bias in the choice
of anecdotes, which the receiver must then account for. This significantly
reduces the informativeness of the signal, leading to substantial utility
loss for both sides. One consequence of this is informational homophily: a
receiver can rationally prefer to obtain information from a poorly-informed
sender with aligned preferences, rather than a knowledgeable expert whose
preferences may differ from her own.

This talk is based on a joint work with Nicole Immorlica, Brendan Lucier,
Markus Mobius, and Divyarthi Mohan.
*Speaker:* Jaawad Noor
*Title:* *Intuitive Beliefs*
*Abstract: *A probability measure over a multi-dimensional state space is
an Intuitive Belief if it is an aggregation of pairwise associations which
have been formed on the basis of past experience in the environment.
Associations are shown to correspond to an analog of pointwise mutual
information, and a separability property in beliefs is shown to
characterize the model. The formation of associations is modelled as an
extension of machine learning. Intuitive Beliefs are shown to exaggerate
correlations in low probability states, exhibit the Disposition Effect
documented in behavioral finance, and belief patterns observed in the
psychology literature on overconfidence.

Hope to see you all there virtually!
Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20210314/7874e5a4/attachment.html>