= Aaron Roth
{c}
<Aaron Roth> studies <algorithms>, <machine learning> and private data analysis. With <Cynthia Dwork>, he coauthored <The Algorithmic Foundations of Differential Privacy by Cynthia Dwork and Aaron Roth>, developing precise privacy guarantees and mechanisms for data analysis.https://www.cis.upenn.edu/~aaroth/[About Me, research interests]{ref}
For a count query that changes by at most one when a person's record is added or removed, the <Laplace mechanism> adds noise with scale $1/\epsilon$ to obtain $\epsilon$-<differential privacy>. Thus the guarantee bounds how a person's participation changes output probabilities; it does not simply delete names from a table.<The Algorithmic Foundations of Differential Privacy by Cynthia Dwork and Aaron Roth>[§2.3, Definition 2.4; §3.3, Theorem 3.6]{ref}
\Image[https://directory.engineering.upenn.edu/wp-content/uploads/2020/03/Roth-Aaron.jpg]
{title=Portrait of <Aaron Roth>}
{source=https://directory.engineering.upenn.edu/aaron-roth/}
{width=240}
Back to article page
