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 Shift Toward Open and Reproducible AI Research," Under Review, 2026. doi: 10.48550/arXiv.2606.16974..

Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems

Authors: Roie Reshef, Kfir Yehuda Levy

ICML 2024 | Venue PDF | LLM Run Details | Input Tokens: 28,337 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,074 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.

Reproducibility Variable Result LLM Response
Research Type Experimental We ran DP-ยต2on MNIST using a logistic regression model in the untrusted server case. The parameters are G = 2 785 = 39.6, L = 785/2 = 392.5, D = 0.1, which brings us S = 118.1. Our model has d = 10 785 = 7850 parameters. We kept M T = 60,000, and checked M = 1, 10, 100 and ฯ = 4, 8, 16. We show our results in Table 1.
Researcher Affiliation Academia 1Department of Electrical and Computer Engineering, Technion, Haifa, Israel.
Pseudocode Yes Algorithm 1 DP-ยต2-FL for Untrusted Server Algorithm 2 DP-ยต2-FL for Trusted Server
Open Source Code No The paper does not provide an explicit statement or link to its open-source code for the described methodology.
Open Datasets Yes We ran DP-ยต2on MNIST using a logistic regression model in the untrusted server case.
Dataset Splits No The paper mentions 'MNIST' and that 'M T = 60,000' but does not specify the explicit percentages or sample counts for training, validation, and test splits, nor does it refer to a standard split method with a citation.
Hardware Specification No The paper mentions running experiments but does not specify any hardware details like GPU models, CPU types, or memory.
Software Dependencies No The paper describes the algorithms and their theoretical properties but does not list any specific software dependencies with version numbers.
Experiment Setup Yes We ran DP-ยต2on MNIST using a logistic regression model in the untrusted server case. The parameters are G = 2 785 = 39.6, L = 785/2 = 392.5, D = 0.1, which brings us S = 118.1. Our model has d = 10 785 = 7850 parameters. We kept M T = 60,000, and checked M = 1, 10, 100 and ฯ = 4, 8, 16.