Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Differential Privacy for Growing Databases

Authors: Rachel Cummings, Sara Krehbiel, Kevin A. Lai, Uthaipon Tantipongpipat

NeurIPS 2018 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The paper focuses on algorithm design, proofs, and mathematical analysis of privacy and accuracy guarantees. It presents theorems, lemmas, and theoretical comparisons (e.g., Table 2 compares asymptotic accuracy guarantees for different differential privacy settings). There are no sections describing empirical studies, datasets, experimental results, or performance metrics from actual implementations. For example, Section 3.1 describes 'Private multiplicative weights for growing databases (PMWG)' and immediately follows it with 'Theorem 5' and a 'Proof sketch', indicating a theoretical analysis.
Researcher Affiliation Academia Rachel Cummings Georgia Institute of Technology, Sara Krehbiel University of Richmond, Kevin A. Lai Georgia Institute of Technology, Uthaipon Tantipongpipat Georgia Institute of Technology
Pseudocode Yes Our algorithm for PMW for growing databases (PMWG) is given as Algorithm 1 in Appendix B.
Open Source Code No The paper provides pseudocode (Algorithm 1 in Appendix B) but does not mention or provide links to any open-source code repositories for the implemented methodology.
Open Datasets No The paper is theoretical and focuses on algorithm design and proofs of privacy and accuracy guarantees. It defines abstract databases ('a database over some ๏ฌxed data universe X of ๏ฌnite size N') but does not mention the use of specific, publicly available datasets for experimental training or evaluation.
Dataset Splits No The paper does not describe conducting empirical experiments with datasets, and therefore, it does not provide any information about training, validation, or test dataset splits.
Hardware Specification No The paper does not describe conducting experiments or implementations, and therefore, no hardware specifications are mentioned.
Software Dependencies No The paper does not describe conducting experiments or implementations, and therefore, no specific software dependencies with version numbers are mentioned.
Experiment Setup No The paper is theoretical and does not describe conducting empirical experiments. Therefore, no experimental setup details, such as hyperparameters or training settings, are provided.