Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms

Authors: Thomas Berrett, Cristina Butucea

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We find separation rates for testing multinomial or more general discrete distributions under the constraint of α-local differential privacy. We construct efficient randomized algorithms and test procedures, in both the case where only noninteractive privacy mechanisms are allowed and also in the case where all sequentially interactive privacy mechanisms are allowed. We prove general information theoretical bounds that allow us to establish the optimality of our algorithms among all pairs of privacy mechanisms and test procedures, in most usual cases.
Researcher Affiliation Academia Berrett Thomas CREST, ENSAE, IP Paris 5, avenue Henry le Chatelier 91120 Palaiseau Cedex, FRANCE thomas.berrett@ensae.fr Butucea Cristina CREST, ENSAE, IP Paris 5, avenue Henry le Chatelier 91120 Palaiseau Cedex, FRANCE cristina.butucea@ensae.fr
Pseudocode No The paper describes algorithms and procedures in descriptive text and mathematical formulas but does not include structured pseudocode blocks or clearly labeled 'Algorithm' sections.
Open Source Code No The paper does not contain any statement about releasing source code or provide links to a code repository.
Open Datasets No This is a theoretical paper focused on deriving optimal separation rates and proving information theoretical bounds for statistical testing. It does not conduct experiments with empirical datasets, therefore, there is no mention of publicly available or open datasets.
Dataset Splits No This is a theoretical paper focused on deriving optimal separation rates and proving information theoretical bounds. It does not conduct experiments with empirical datasets, and therefore does not specify training, validation, or test dataset splits.
Hardware Specification No This is a theoretical paper that does not involve computational experiments requiring specific hardware. Therefore, no hardware specifications are mentioned.
Software Dependencies No This is a theoretical paper that does not involve computational experiments requiring specific software. Therefore, no software dependencies with version numbers are mentioned.
Experiment Setup No This is a theoretical paper focused on deriving optimal separation rates and proving information theoretical bounds. It does not describe an experimental setup, hyperparameters, or system-level training settings.