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..
Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates
Authors: Andrew Lowy, Daogao Liu
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This paper focuses on theoretical analysis and does not include experimental results. |
| Researcher Affiliation | Collaboration | Andrew Lowy CISPA Helmholtz Center for Information Security EMAIL Daogao Liu Google Research EMAIL |
| Pseudocode | Yes | Algorithm 1: A Second-Order DP Bilevel Optimization Algorithm Algorithm 2: Warm-Start Meta-Algorithm for Bilevel ERM |
| Open Source Code | No | This paper focuses on theoretical analysis and does not include experimental results. While our theoretical rates are nearly optimal, empirical performance can depend on implementation details, constant factors, and practical optimization challenges not captured in our analysis. We defer empirical validation, including runtime measurements and real-data utility evaluation, to future work. |
| Open Datasets | No | This paper focuses on theoretical analysis and does not include experimental results. This paper focuses on theoretical developments and does not include empirical evaluation or deployment. |
| Dataset Splits | No | This paper focuses on theoretical analysis and does not include experimental results. This paper focuses on theoretical developments and does not include empirical evaluation or deployment. |
| Hardware Specification | No | The paper does not include experiments. |
| Software Dependencies | No | The paper does not include experiments. |
| Experiment Setup | No | The paper does not include experiments. |