194 citations · 280 across the 3 of their papers we have counts for
4 papers
Descent-to-Delete: Gradient-Based Methods for Machine Unlearning
Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi
We study the data deletion problem for convex models. By leveraging techniques from convex optimization and reservoir sampling, we give the first data deletion algorithms that are…
Optimal, Truthful, and Private Securities Lending
Emily Diana, Michael Kearns, Seth Neel +1
We consider a fundamental dynamic allocation problem motivated by the problem of in financial markets, the mechanism underlying the short selling of s…
A Convex Framework for Fair Regression
Richard Berk, Hoda Heidari, Shahin Jabbari +5
We introduce a flexible family of fairness regularizers for (linear and logistic) regression problems. These regularizers all enjoy convexity, permitting fast optimization, and the…
Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM
Katrina Ligett, Seth Neel, Aaron Roth +2
Traditional approaches to differential privacy assume a fixed privacy requirement for a computation, and attempt to maximize the accuracy of the computation subject to the priv…