Locally differentially private estimation of functionals of discrete distributions
Authors: Cristina Butucea, Yann ISSARTEL
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We study the problem of estimating non-linear functionals of discrete distributions in the context of local differential privacy. The initial data x1, . . . , xn [K] are supposed i.i.d. and distributed according to an unknown discrete distribution p = (p1, . . . , p K). Only α-locally differentially private (LDP) samples z1, ..., zn are publicly available, where the term local means that each zi is produced using one individual attribute xi. We exhibit privacy mechanisms (PM) that are sequentially interactive (i.e. they are allowed to use already published confidential data) or non-interactive. We describe the behavior of the quadratic risk for estimating the power sum functional Fγ = PK k=1 pγ k, γ > 0 as a function of K, n and α. |
| Researcher Affiliation | Academia | Cristina Butucea CREST, ENSAE, IP Paris Palaiseau 91120 Cedex, France cristina.butucea@ensae.fr Yann Issartel CREST, ENSAE, IP Paris Palaiseau 91120 Cedex, France yann.issartel@ensae.fr |
| Pseudocode | No | The paper describes algorithms and procedures using mathematical formulas and descriptive text (e.g., in sections 2.3, 2.4, 2.5), but it does not include formal pseudocode blocks or sections labeled "Algorithm". |
| Open Source Code | No | The paper does not provide any statements about making source code publicly available for the methodology described. |
| Open Datasets | No | The paper is theoretical and does not conduct experiments on specific datasets. It refers to "samples" in a mathematical context (e.g., "n i.i.d. samples x1, ..., xn"), but does not mention any publicly available or open datasets used for training or evaluation. |
| Dataset Splits | No | The paper is theoretical and does not involve experimental validation on specific dataset splits. Therefore, it does not provide details on training/test/validation dataset splits. |
| Hardware Specification | No | The paper does not mention any specific hardware used for computations or experiments, as it is a theoretical work. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers. It focuses on mathematical derivations and theoretical analysis. |
| Experiment Setup | No | The paper is theoretical and does not detail an experimental setup with hyperparameters or training configurations, as it does not involve empirical training or evaluation. |