Privacy-Aware Sequential Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yuxin, Rahimian, M. Amin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915529623601152
author Liu, Yuxin
Rahimian, M. Amin
author_facet Liu, Yuxin
Rahimian, M. Amin
contents In settings like vaccination registries, individuals act after observing others, and the resulting public records can expose private information. We study privacy-preserving sequential learning, where agents add endogenous noise to their reported actions to conceal private signals. Efficient social learning relies on information flow, seemingly in conflict with privacy. Surprisingly, with continuous signals and a fixed privacy budget $(ε)$, the optimal randomization strategy balances privacy and accuracy, accelerating learning to $Θ_ε(\log n)$, faster than the nonprivate $Θ(\sqrt{\log n})$ rate. In the nonprivate baseline, the expected time to the first correct action and the number of incorrect actions diverge; under privacy with sufficiently small $ε$, both are finite. Privacy helps because, under the false state, agents more often receive signals contradicting the majority; randomization then asymmetrically amplifies the log-likelihood ratio, enhancing aggregation. In heterogeneous populations, an order-optimal $Θ(\sqrt{n})$ rate is achievable when a subset of agents have low privacy budgets. With binary signals, however, privacy reduces informativeness and impairs learning relative to the nonprivate baseline, though the dependence on $ε$ is nonmonotone. Our results show how privacy reshapes information dynamics and inform the design of platforms and policies.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19525
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Privacy-Aware Sequential Learning
Liu, Yuxin
Rahimian, M. Amin
Theoretical Economics
Cryptography and Security
Social and Information Networks
Probability
Applications
In settings like vaccination registries, individuals act after observing others, and the resulting public records can expose private information. We study privacy-preserving sequential learning, where agents add endogenous noise to their reported actions to conceal private signals. Efficient social learning relies on information flow, seemingly in conflict with privacy. Surprisingly, with continuous signals and a fixed privacy budget $(ε)$, the optimal randomization strategy balances privacy and accuracy, accelerating learning to $Θ_ε(\log n)$, faster than the nonprivate $Θ(\sqrt{\log n})$ rate. In the nonprivate baseline, the expected time to the first correct action and the number of incorrect actions diverge; under privacy with sufficiently small $ε$, both are finite. Privacy helps because, under the false state, agents more often receive signals contradicting the majority; randomization then asymmetrically amplifies the log-likelihood ratio, enhancing aggregation. In heterogeneous populations, an order-optimal $Θ(\sqrt{n})$ rate is achievable when a subset of agents have low privacy budgets. With binary signals, however, privacy reduces informativeness and impairs learning relative to the nonprivate baseline, though the dependence on $ε$ is nonmonotone. Our results show how privacy reshapes information dynamics and inform the design of platforms and policies.
title Privacy-Aware Sequential Learning
topic Theoretical Economics
Cryptography and Security
Social and Information Networks
Probability
Applications
url https://arxiv.org/abs/2502.19525