Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Private Query Release Assisted by Public Data
Authors: Raef Bassily, Albert Cheu, Shay Moran, Aleksandar Nikolov, Jonathan Ullman, Steven Wu
ICML 2020 | Venue PDF | LLM Run Details | Input Tokens: 17,271 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,002 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Our upper and lower bounds on the private sample complexity have matching dependence on the dual VC-dimension of H. For a large category of query classes, our bounds on the public sample complexity have matching dependence on α. (from Abstract) and Upper bounds: We give a construction of a PAP algorithm that solves the query release problem... (from Section 1.1) and Lower bound on private sample complexity: The proof of the lower bound is based on the robust tracing attack... (from Section 1.2) and Theorem 10 (Upper Bound). APAP (Algorithm 3) is an (α, β, ε, δ) public-data-assisted private query-release algorithm... (from Section 3) |
| Researcher Affiliation | Collaboration | Raef Bassily 1 Albert Cheu 2 Shay Moran 3 Aleksandar Nikolov 4 Jonathan Ullman 2 Zhiwei Steven Wu 5 1Department of Computer Science & Engineering, The Ohio State University. 2Khoury College of Computer Sciences, Northeastern University 3Google AI Princeton 4Department of Computer Science, University of Toronto 5Department of Computer Science and Engineering, University of Minnesota. |
| Pseudocode | Yes | Algorithm 1 An outline for the Private Multiplicative Weights Algorithm (PMW); Algorithm 2 An outline for a generic Public-data-Assisted Private (PAP) algorithm for query release; Algorithm 3 APAP Public-data-assisted Private Query Release Algorithm |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code for the described methodology, nor does it provide any links to a code repository. |
| Open Datasets | No | The paper uses abstract concepts like "distribution D over X" and "data set x of i.i.d. samples" but does not refer to any specific named or publicly accessible dataset used for training. |
| Dataset Splits | No | The paper is theoretical and does not describe empirical experiments with 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 describes algorithms and theoretical analyses but does not mention any specific software dependencies or their version numbers. |
| Experiment Setup | No | The paper is theoretical and does not describe an experimental setup, hyperparameters, or training configurations. |