Search Results for author:
Found 25 papers, 9 papers with code
Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers
In this write-up, we address this shortcoming by providing an accessible overview of existing literature related to operationalizing regulatory principles.
To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models
In fair machine learning, one source of performance disparities between groups is over-fitting to groups with relatively few training samples.
Measuring and mitigating voting access disparities: a study of race and polling locations in Florida and North Carolina
In this paper, we quantify access to polling locations, developing a methodology for the calibrated measurement of racial disparities in polling location "load" and distance to polling locations.
Repairing Regressors for Fair Binary Classification at Any Decision Threshold
We study the problem of post-processing a supervised machine-learned regressor to maximize fair binary classification at all decision thresholds.
Shapley Residuals: Quantifying the limits of the Shapley value for explanations
Popular feature importance techniques compute additive approximations to nonlinear models by first defining a cooperative game describing the value of different subsets of the model's features, then calculating the resulting game's Shapley values to attribute credit additively between the features.
Precarity: Modeling the Long Term Effects of Compounded Decisions on Individual Instability
When it comes to studying the impacts of decision making, the research has been largely focused on examining the fairness of the decisions, the long-term effects of the decision pipelines, and utility-based perspectives considering both the decision-maker and the individuals.
Interdisciplinary Approaches to Understanding Artificial Intelligence's Impact on Society
Innovations in AI have focused primarily on the questions of "what" and "how"-algorithms for finding patterns in web searches, for instance-without adequate attention to the possible harms (such as privacy, bias, or manipulation) and without adequate consideration of the societal context in which these systems operate.
Information access representations and social capital in networks
Social network position confers power and social capital.
Social and Information Networks
Fair clustering via equitable group representations
A core principle in most clustering problems is that a cluster center should be representative of the cluster it represents, by being "close" to the points associated with it.
Problems with Shapley-value-based explanations as feature importance measures
Game-theoretic formulations of feature importance have become popular as a way to "explain" machine learning models.
Equalizing Recourse across Groups
We measure recourse as the distance of an individual from the decision boundary of a classifier.
Disentangling Influence: Using Disentangled Representations to Audit Model Predictions
Specifically, we show that disentangled representations provide a mechanism to identify proxy features in the dataset, while allowing an explicit computation of feature influence on either individual outcomes or aggregate-level outcomes.
Fairness in representation: quantifying stereotyping as a representational harm
While harms of allocation have been increasingly studied as part of the subfield of algorithmic fairness, harms of representation have received considerably less attention.
A comparative study of fairness-enhancing interventions in machine learning
Concretely, we present the results of an open benchmark we have developed that lets us compare a number of different algorithms under a variety of fairness measures, and a large number of existing datasets.
Fair Pipelines
This work facilitates ensuring fairness of machine learning in the real world by decoupling fairness considerations in compound decisions.
Runaway Feedback Loops in Predictive Policing
Predictive policing systems are increasingly used to determine how to allocate police across a city in order to best prevent crime.
On the (im)possibility of fairness
We show that in order to prove desirable properties of the entire decision-making process, different mechanisms for fairness require different assumptions about the nature of the mapping from construct space to decision space.
A Unified View of Localized Kernel Learning
Multiple Kernel Learning, or MKL, extends (kernelized) SVM by attempting to learn not only a classifier/regressor but also the best kernel for the training task, usually from a combination of existing kernel functions.
Auditing Black-box Models for Indirect Influence
It is therefore hard to acquire a deeper understanding of model behavior, and in particular how different features influence the model prediction.
A Group Theoretic Perspective on Unsupervised Deep Learning
Over the shadow groups, the pre-training step, originally introduced as a mechanism to better initialize a network, becomes equivalent to a search for features with minimal orbits.
Why does Deep Learning work? - A perspective from Group Theory
Over the shadow groups, the pre-training step, originally introduced as a mechanism to better initialize a network, becomes equivalent to a search for features with minimal orbits.
Power to the Points: Validating Data Memberships in Clusterings
It is also efficient: assigning an affinity score to a point depends only polynomially on the number of clusters and is independent of the number of points in the data.
A Geometric Algorithm for Scalable Multiple Kernel Learning
We present a geometric formulation of the Multiple Kernel Learning (MKL) problem.
An Information-Theoretic Approach to Detecting Changes in Multi-Dimensional Data Streams
In this paper, we take a general, information-theoretic approach to the change detection problem, which works for multidimensional as well as categorical data.
