Work

Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization

Year: 2024

Type: preprint

Abstract: In this work, we give a new technique for analyzing individualized privacy accounting via the following simple observation: if an algorithm is one-sided add-DP, then its subsampled variant satisfies two-sided DP. From this, we obtain several improved algorithms for private combinatorial optimization problems, including decomposable submodular maximization and set cover. Our error guarantees are asymptotically tight and our algorithm satisfies pure-DP while previously known algorithms (Gupta et al., 2010; Chaturvedi et al., 2021) are approximate-DP. We also show an application of our technique beyond combinatorial optimization by giving a pure-DP algorithm for the shifting heavy hitter problem in a stream; previously, only an approximateDP algorithm was known (Kaplan et al., 2021; Cohen & Lyu, 2023).

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2405.18534

Authors: Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Manurangsi, Pasin, Sealfon, Adam

Institution: Google (United States)

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4399197850

Cites:

Cited by:

Related to: 10