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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
Authors: Bar Mahpud, Or Sheffet
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This is a theoretical paper that does not include empirical experiments. All claims are supported by formal definitions, theorems, and complete proofs, making experimental reproducibility not applicable. |
| Researcher Affiliation | Academia | Bar Mahpud Faculty of Engineering Bar-Ilan University Israel EMAIL Or Sheffet Faculty of Engineering Bar-Ilan University Israel EMAIL |
| Pseudocode | Yes | Algorithm 1 DP Second Moment Estimation Input: a (m, α, β)-subsamplable set of n points X Rd, parameters: error parameter ξ (0, 1), privacy parameter ρ, covering radius R. ... Algorithm 2 Recursive DP Second Moment Estimation (Rec DPSME) Input: a set of n points X Rd, parameters: linear shrinking η < 1, eigenvalue threshold ψ < 1, stopping value C, noise c, eigenvalue upper bound κ, radius R, iterations bound T, error parameter ξ, privacy loss ρ. |
| Open Source Code | No | This paper is entirely theoretical and does not include empirical experiments or datasets. As such, no code or data is necessary to reproduce the main results, and this question is not applicable. |
| Open Datasets | No | This paper is entirely theoretical and does not include empirical experiments or datasets. As such, no code or data is necessary to reproduce the main results, and this question is not applicable. |
| Dataset Splits | No | This is a theoretical work that does not involve empirical experiments, training, or testing. Therefore, specifications such as data splits, hyperparameters, or optimizers are not applicable. |
| Hardware Specification | No | The paper contains no empirical experiments or statistical evaluations; all results are theoretical and supported by formal analysis and proofs. Hence, reporting error bars or statistical significance is not applicable. |
| Software Dependencies | No | This is a theoretical work that does not involve empirical experiments, training, or testing. Therefore, specifications such as data splits, hyperparameters, or optimizers are not applicable. |
| Experiment Setup | No | This is a theoretical work that does not involve empirical experiments, training, or testing. Therefore, specifications such as data splits, hyperparameters, or optimizers are not applicable. |