We introduce a new differentially private regression setting we call Pri...
In recent years, there has been a flurry of research focusing on the fai...
As predictive models are increasingly being employed to make consequenti...
Data deletion algorithms aim to remove the influence of deleted data poi...
We study the data deletion problem for convex models. By leveraging
tech...
We consider a fundamental dynamic allocation problem motivated by the pr...
We give a new proof of the "transfer theorem" underlying adaptive data
a...
One of the most effective algorithms for differentially private learning...
We revisit the notion of individual fairness first proposed by Dwork et ...
We study the power of interactivity in local differential privacy. First...
We develop theory for using heuristics to solve computationally hard pro...
Settings such as lending and policing can be modeled by a centralized ag...
Kearns et al. [2018] recently proposed a notion of rich subgroup fairnes...
Data that is gathered adaptively --- via bandit algorithms, for example ...
The most prevalent notions of fairness in machine learning are statistic...
We introduce a flexible family of fairness regularizers for (linear and
...