papers

Publications (25)

cs.LG2023

Better Private Linear Regression Through Better Private Feature Selection

Travis Dick, Jennifer Gillenwater, Matthew Joseph

Existing work on differentially private linear regression typically assumes that end users can precisely set data bounds or algorithmic hyperparameters. End users often struggle to…

cs.CR2023

Learning-Augmented Private Algorithms for Multiple Quantile Release

Mikhail Khodak, Kareem Amin, Travis Dick +1

When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors. We pro…

cs.CR2023

Measuring Re-identification Risk

CJ Carey, Travis Dick, Alessandro Epasto +8

Compact user representations (such as embeddings) form the backbone of personalization services. In this work, we present a new theoretical framework to measure re-identification r…

cs.LG2024

Auditing Privacy Mechanisms via Label Inference Attacks

Róbert István Busa-Fekete, Travis Dick, Claudio Gentile +3

We propose reconstruction advantage measures to audit label privatization mechanisms. A reconstruction advantage measure quantifies the increase in an attacker's ability to infer t…

cs.LG2024

Subset-Based Instance Optimality in Private Estimation

Travis Dick, Alex Kulesza, Ziteng Sun +1

We propose a new definition of instance optimality for differentially private estimation algorithms. Our definition requires an optimal algorithm to compete, simultaneously for eve…

cs.LG2026

AI-rithmetic

Alex Bie, Travis Dick, Alex Kulesza +3

Modern AI systems have been successfully deployed to win medals at international math competitions, assist with research workflows, and prove novel technical lemmas. However, despi…