Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Back to Paper
cs.CR

Local ID: 2604.15596v4

AI Summary: gemma4:e4b

Privacy, Prediction, and Allocation

By Ben Jacobsen, Nitin Kohli

Revision History Timeline

v14/17/2026
4/17/2026

“2026 FORC (Foundations of Responsible Computing)”

v24/23/2026
4/23/2026

“2026 FORC (Foundations of Responsible Computing)”

v36/2/2026
6/2/2026

“2026 FORC (Foundations of Responsible Computing)”

v46/4/2026
6/4/2026

“2026 FORC (Foundations of Responsible Computing)”

★ Version indexed in Explorer

Comparing v3 vs v4

Green = Added • Red = Removed

Title Comparison

Privacy, Prediction, and Allocation

Authors Comparison

No author changes.

v3 Comment

“2026 FORC (Foundations of Responsible Computing)”

v4 Comment

“2026 FORC (Foundations of Responsible Computing)”

Abstract Word Diff

Algorithmic predictions are increasingly used to inform the allocation of scarce resources. The promise of these methods is that, through machine learning, they can better identify the people who would benefit most from interventions. Recently, however, several works have called this assumption into question by demonstrating the existence of settings where simple, unit-level allocation strategies can meet or even exceed the performance of those based on individual-level targeting. Separately, other works have objected to individual-level targeting on privacy grounds, leading to an unusual situation where a single solution, unit-level targeting, is recommended for reasons of both privacy and utility. Motivated by the desire to fully understand the interplay of privacy and targeting levels, we initiate the study of aid allocation systems that satisfy differential privacy, synthesizing existing works on private optimization with the economic models of aid allocation used in the non-private literature. To this end, we investigate private variants of both individual and unit-level allocation strategies in both stochastic and distribution-free settings under a range of constraints on data availability. Through this analysis, we provide clean, interpretable bounds characterizing the tradeoffs between privacy, efficiency, and targeting precision in allocation.
View Full Version History on arXiv