Locally Private Gaussian Estimation

Authors: Matthew Joseph, Janardhan Kulkarni, Jieming Mao, Steven Z. Wu

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We match these upper bounds with an information-theoretic lower bound showing that our accuracy guarantees are tight up to logarithmic factors for all sequentially interactive locally private protocols.
Researcher Affiliation Collaboration Matthew Joseph University of Pennsylvania majos@cis.upenn.edu Janardhan Kulkarni Microsoft Research Redmond jakul@microsoft.com Jieming Mao Google Research New York maojm@google.com Zhiwei Steven Wu University of Minnesota zsw@umn.edu
Pseudocode Yes Algorithm 1 KVGAUSSTIMATE, Algorithm 2 KVAGG1, Algorithm 3 ESTMEAN, Algorithm 4 KVRR2, Algorithm 5 KVAGG2, Algorithm 6 UVGAUSSTIMATE
Open Source Code No The paper does not provide any statements or links regarding the public availability of source code for the described methodology.
Open Datasets No The paper is theoretical and focuses on estimation problem with i.i.d. samples from a Gaussian distribution, without referring to any specific publicly available dataset or providing access information for one.
Dataset Splits No The paper is theoretical and does not involve empirical experiments requiring dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and focuses on algorithm design and proofs rather than empirical experimental setup details like hyperparameters or training configurations.