Privacy-Resolution Tradeoff for Adaptive Noisy Twenty Questions Estimation

TL;DR

This paper investigates the balance between privacy and accuracy in adaptive noisy twenty questions estimation, proposing a new private query method that improves performance over previous approaches, especially in noiseless scenarios.

Contribution

It introduces a two-stage private query procedure for noisy twenty questions estimation, analyzing its performance and demonstrating improvements over prior methods in noiseless cases.

Findings

Proposed a two-stage private query procedure for noisy estimation.

Analyzed non-asymptotic and asymptotic performance of the method.

Achieved better performance than previous methods in noiseless scenarios.

Abstract

We revisit noisy twenty questions estimation and study the privacy-resolution tradeoff for adaptive query procedures. Specifically, in twenty questions estimation, there are two players: an oracle and a questioner. The questioner aims to estimate target variables by posing queries to the oracle that knows the variables and using noisy responses to form reliable estimates. Typically, there are adaptive and non-adaptive query procedures. In adaptive querying, one designs the current query using previous queries and their noisy responses while in non-adaptive querying, all queries are posed simultaneously. Generally speaking, adaptive query procedures yield better performance. However, adaptive querying leads to privacy concerns, which were first studied by Tsitsiklis, Xu and Xu (COLT 2018) and by Xu, Xu and Yang (AISTATS 2021) for the noiseless case, where the oracle always provides correct answers to queries. In this paper, we generalize the above results to the more practical noisy case, by proposing a two-stage private query procedure, analyzing its non-asymptotic and second-order asymptotic achievable performance and discussing the impact of privacy concerns. Furthermore, when specialized to the noiseless case, our private query procedure achieves better performance than above-mentioned query procedures (COLT 2018, AISTATS 2021).