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 Statistical Estimation via Truncation
Authors: Manolis Zampetakis, Felix Zhou
NeurIPS 2025 | Venue PDF | LLM Run Details | Input Tokens: 33,206 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 2,555 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 | Justification: Our contributions are purely theoretical. |
| Researcher Affiliation | Academia | Manolis Zampetakis Yale University EMAIL Felix Zhou Yale University EMAIL |
| Pseudocode | Yes | Our main DP-SGD subroutine can be found in Algorithm B.1, which we defer to Appendix B.4 due to space constraints. We present a simplified version below for convenience: ... Pseudocode. See Algorithm B.2 for pseudocode of the warm-start algorithm. ... Pseudocode. See Algorithm B.3 for pseudocode. |
| Open Source Code | No | Justification: Our contributions are purely theoretical. The answer NA means that the paper does not include experiments requiring code. |
| Open Datasets | No | Justification: Our contributions are purely theoretical. The answer NA means that the paper does not include experiments. |
| Dataset Splits | No | Justification: Our contributions are purely theoretical. The answer NA means that the paper does not include experiments. |
| Hardware Specification | No | Justification: Our contributions are purely theoretical. The answer NA means that the paper does not include experiments. |
| Software Dependencies | No | Justification: Our contributions are purely theoretical. The answer NA means that the paper does not include experiments. |
| Experiment Setup | No | Justification: Our contributions are purely theoretical. The answer NA means that the paper does not include experiments. |