Private Identity Testing for High-Dimensional Distributions

Authors: Clément L. Canonne, Gautam Kamath, Audra McMillan, Jonathan Ullman, Lydia Zakynthinou

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our main contribution is to give novel algorithms for hypothesis testing of high-dimensional distributions with improved sample complexity. In particular, we give differentially private algorithms for the following fundamental problems:
Researcher Affiliation Collaboration Clément Canonne IBM Research, Almaden ccanonne@cs.columbia.edu; Gautam Kamath Cheriton School of Computer Science University of Waterloo g@csail.mit.edu; Audra Mc Millan Khoury College of Computer Sciences, Northeastern University Department of Computer Science, Boston University audramarymcmillan@gmail.com; Jonathan Ullman Khoury College of Computer Sciences Northeastern University jullman@ccs.neu.edu; Lydia Zakynthinou Khoury College of Computer Sciences Northeastern University zakynthinou.l@northeastern.edu
Pseudocode Yes Algorithm 1 LIPEXTTEST; Algorithm 2 Private Uniformity Testing via Lipschitz Extension
Open Source Code No The paper does not provide any links to open-source code or state that code is made available.
Open Datasets No The paper discusses theoretical sample complexity for distributions (e.g., "product distribution P over { 1}d", "multivariate Gaussian P in Rd") rather than empirical evaluation on specific named datasets. Therefore, no access information for a public dataset is provided.
Dataset Splits No The paper does not mention any training, validation, or test dataset splits, as it focuses on theoretical analysis rather than empirical experimentation.
Hardware Specification No The paper focuses on theoretical algorithms and their sample complexity. It does not mention any specific hardware used for running experiments.
Software Dependencies No The paper is theoretical and describes algorithms and proofs. It does not list any software dependencies or version numbers.
Experiment Setup No The paper presents theoretical algorithms and their analysis (e.g., sample complexity). It does not describe any experimental setup details such as hyperparameters, training configurations, or system-level settings.