Dear ML reading group,
This week we will have Deborah presenting the paper *Not So Fair: The Impact of Presumably Fair Machine Learning Models* (paper here https://dl.acm.org/doi/10.1145/3600211.3604699). The reading group will take place on *Wednesday at 2:30pm *as usual, and this time we will host physically at *room 0.01 of building E1.7 @ UdS*. For those attending remotely, you can find the Zoom link in the reading group spreadsheet https://docs.google.com/spreadsheets/d/1vtgEezBqS4d_ACPt-emK2NT52x7nofX9jxgH1N04MQE/edit?usp=sharing.
*Abstract:*
When bias mitigation methods are applied to make fairer machine learning models in fairness-related classification settings, there is an assumption that the disadvantaged group should be better off than if no mitigation method was applied. However, this is a potentially dangerous assumption because a “fair” model outcome does not automatically imply a positive impact for a disadvantaged individual—they could still be negatively impacted. Modeling and accounting for those impacts is key to ensure that mitigated models are not unintentionally harming individuals; we investigate if mitigated models can still negatively impact disadvantaged individuals and what conditions affect those impacts in a loan repayment example. Our results show that most mitigated models negatively impact disadvantaged group members in comparison to the unmitigated models. The domain-dependent impacts of model outcomes should help drive future bias mitigation method development.
Cheers, Adrián
Dear all,
This week we have Kiet Vo from CISPA presenting "Weak Instruments in IV Regression: Theory and Practice" (https://scholar.harvard.edu/files/stock/files/andrews_stock_sun_wirev_011119...)
The reading group will take place on Wednesday at 2:30pm, the location will be somewhere in D2.
For those attending remotely, you can find the Zoom link in the reading group spreadsheethttps://docs.google.com/spreadsheets/d/1vtgEezBqS4d_ACPt-emK2NT52x7nofX9jxgH1N04MQE/edit?usp=sharing.
Abstract:
When instruments are weakly correlated with endogenous regressors, conventional methods for instrumental variables estimation and inference become unreliable. A large literature in econometrics develops procedures for detecting weak instruments and constructing robust confidence sets, but many of the results in this literature are limited to settings with independent and homoskedastic data, while data encountered in practice frequently violate these assumptions. We review the literature on weak instruments in linear IV regression with an emphasis on results for non-homoskedastic (heteroskedastic, serially correlated, or clustered) data. To assess the practical importance of weak instruments, we also report tabulations and simulations based on a survey of papers published in the American Economic Review from 2014 to 2018 that use instrumental variables. These results suggest that weak instruments remain an important issue for empirical practice, and that there are simple steps researchers can take to better handle weak instruments in applications.
Best,
Siu Lun
---
Siu Lun Chau, Ph.D (Oxon) | Postdoctoral Researcher CISPA - Helmholtz Center for Information Security Stuhlsatzenhaus 5, 66123 Saarbrücken, +44 7415137484 | siu-lun.chau@cispa.de | https://chau999.github.io/
ml-reading-group@lists.saarland-informatics-campus.de
-
Adrián Javaloy -
Siu Lun Chau