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..
Constrained Optimization From a Control Perspective via Feedback Linearization
Authors: Runyu Zhang, Arvind Raghunathan, Jeff Shamma, Na Li
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 6 Numerical Verifications For numerical validation, we consider a logistic regression problem involving heterogeneous clients [73, 42]. ... The results of the numerical simulation are presented in Figure 2. ... Figure 5 presents the numerical results for solving AC OPF on the IEEE-39 and IEEE-118 bus systems, respectively. |
| Researcher Affiliation | Collaboration | Runyu Zhang Massachusetts Institute of Technology EMAIL Arvind Raghunathan Mitsubishi Electric Research Laboratories EMAIL Jeff Shamma University of Illinois Urbana-Champaign EMAIL Na Li Harvard University EMAIL |
| Pseudocode | No | The paper describes methods using mathematical equations and derivations (e.g., equations (6), (13), (18), (19), (20)) but does not present them in structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Answer: [Yes] Justification: An anonymized version of the code and data is included in the supplemental material |
| Open Datasets | Yes | Answer: [Yes] Justification: An anonymized version of the code and data is included in the supplemental material |
| Dataset Splits | No | The paper describes data generation parameters for the logistic regression problem (C=5 clients, |Dc|=200, data generated from Bernoulli and Gaussian distributions) and uses standard bus systems (IEEE-39, IEEE-118) for OPF, but it does not specify explicit training, validation, or test dataset splits. |
| Hardware Specification | Yes | Answer: [Yes] Justification: This work is primarily theoretical, and the numerical simulations are simple and lightweight. They were run on a standard personal computer and do not require specialized hardware or significant computational resources, so detailed compute reporting is not necessary. |
| Software Dependencies | No | The paper conducts numerical verifications and presents figures but does not explicitly provide a list of software dependencies with version numbers. |
| Experiment Setup | No | The paper mentions the number of clients (C=5) and dataset size (|Dc|=200) for logistic regression, and the specific bus systems (IEEE-39, IEEE-118) for AC OPF, but it does not provide specific hyperparameter values like learning rates, batch sizes, or optimizer settings used in the simulations. |