73 citations · 585 across the 58 of their papers we have counts for
69 papers
Program Analysis for Adaptive Data Analysis
Jiawen Liu, Weihao Qu, Marco Gaboardi +2
Data analyses are usually designed to identify some property of the population from which the data are drawn, generalizing beyond the specific data sample. For this reason, data an…
Online Matrix Factorization, Online Private Query Release, and Online Discrepancy Minimization
Aleksandar Nikolov, Haohua Tang, Jonathan Ullman
In this paper we consider several related online computation problems. First, we study answering sequences of statistical queries arriving online, and being answered immediately wh…
Lower Bounds for Public-Private Learning under Distribution Shift
Amrith Setlur, Pratiksha Thaker, Jonathan Ullman
The most effective differentially private machine learning algorithms in practice rely on an additional source of purportedly public data. This paradigm is most interesting when th…
Smooth Lower Bounds for Differentially Private Algorithms via Padding-and-Permuting Fingerprinting Codes
Naty Peter, Eliad Tsfadia, Jonathan Ullman
Fingerprinting arguments, first introduced by Bun, Ullman, and Vadhan (STOC 2014), are the most widely used method for establishing lower bounds on the sample complexity or error o…
TMI! Finetuned Models Leak Private Information from their Pretraining Data
John Abascal, Stanley Wu, Alina Oprea +1
Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned…
Differentially Private Medians and Interior Points for Non-Pathological Data
Maryam Aliakbarpour, Rose Silver, Thomas Steinke +1
We construct differentially private estimators with low sample complexity that estimate the median of an arbitrary distribution over satisfying very mild moment condit…