On Differentially Private Sampling from Gaussian and Product Distributions

Authors: Badih Ghazi, Xiao Hu, Ravi Kumar, Pasin Manurangsi

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We present new DP sampling algorithms, and show that they achieve near-optimal sample complexity in the first two settings.
Researcher Affiliation Collaboration Badih Ghazi Google Research Mountain View, CA, US badihghazi@gmail.com Xiao Hu University of Waterloo Waterloo, Canada xiaohu@uwaterloo.ca Ravi Kumar Google Research Mountain View, CA, US ravi.k53@gmail.com Pasin Manurangsi Google Research Bangkok, Thailand pasin@google.com
Pseudocode Yes Algorithm 1 SPHERICALGAUSSIANSAMPLER Parameters: B, σ > 0, and n N. Sample X1, . . . , Xn D for i = 1, . . . , n do Xtrunc i = trunc2 B(Xi) see (1) Sample Z N(0, σ2I) return Z + 1 i [n] Xtrunc i
Open Source Code No The paper does not provide any statement or link regarding the release of open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not use or refer to any specific publicly available datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not describe empirical experiments, thus no dataset split information is provided.
Hardware Specification No The paper is theoretical and does not describe empirical experiments, thus no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe empirical experiments, thus no specific software dependencies with version numbers are provided.
Experiment Setup No The paper is theoretical and does not describe empirical experiments, thus no specific experimental setup details like hyperparameters or training configurations are provided.