• Publications
  • Influence
Datasheets for Datasets
The machine learning community currently has no standardized process for documenting datasets, which can lead to severe consequences in high-stakes domains. To address this gap, we propose datasheetsExpand
Fairness in Learning: Classic and Contextual Bandits
We introduce the study of fairness in multi-armed bandit problems. Our fairness definition can be interpreted as demanding that given a pool of applicants (say, for college admission or mortgages), aExpand
Learning Simple Auctions
TLDR
We present a general framework for proving polynomial sample complexity bounds for the problem of learning from samples the best auction in a class of "simple" auctions. Expand
A Convex Framework for Fair Regression
TLDR
We introduce a flexible family of fairness regularizers for (linear and logistic) regression problems. Expand
On the Pseudo-Dimension of Nearly Optimal Auctions
TLDR
We introduce t-level auctions to interpolate between simple auctions, such as welfare maximization with reserve prices, and optimal auctions, thereby balancing the competing demands of expressivity and simplicity. Expand
The Price of Fair PCA: One Extra Dimension
TLDR
We investigate whether the standard dimensionality reduction technique of PCA inadvertently produces data representations with different fidelity for two different populations. Expand
Guarantees for Spectral Clustering with Fairness Constraints
TLDR
We study a version of constrained spectral clustering (SC) for partitioning graph data in which we try to incorporate the fairness notion proposed by Chierichetti et al. into SC. Expand
The Pseudo-Dimension of Near-Optimal Auctions
TLDR
We introduce t-level auctions to interpolate between simple auctions, such as welfare maximization with reserve prices, and optimal auctions, thereby balancing the competing demands of expressivity and simplicity. Expand
Predictive Inequity in Object Detection
TLDR
In this work, we investigate whether state-of-the-art object detection systems have equitable predictive performance on pedestrians with different skin tones. Expand
Fair k-Center Clustering for Data Summarization
TLDR
We study a setting where the data set comprises several demographic groups and we are restricted to choose $k_i$ prototypes belonging to group $i$. Expand
...
1
2
3
4
5
...