Network change point localisation under local differential privacy
Authors: Mengchu Li, Tom Berrett, Yi Yu
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes] Code is available on openreview. Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] See Appendix A in the supplementary material. Did you report error bars (e.g., with respect to the random seed after running experiments multiple times)? [Yes] We report the median as a substitute. |
| Researcher Affiliation | Academia | Mengchu Li Department of Statistics University of Warwick mengchu.li@warwick.ac.uk Thomas B. Berrett Department of Statistics University of Warwick tom.berrett@warwick.ac.uk Yi Yu Department of Statistics University of Warwick yi.yu.2@warwick.ac.uk |
| Pseudocode | Yes | Algorithm 1 Network Binary Segmentation. |
| Open Source Code | Yes | Code is available on openreview. |
| Open Datasets | No | The paper mentions 'Netflix data set' as an example but does not provide concrete access information (link, DOI, specific citation with authors/year) for any dataset used in experiments. The ethics statement indicates training details are in the appendix, but not dataset access. |
| Dataset Splits | No | The main text of the paper does not provide specific details on training, validation, or test dataset splits (e.g., percentages, sample counts, or citations to predefined splits). While the ethics statement points to an appendix for training details, these are not in the main paper as required. |
| Hardware Specification | No | The paper does not explicitly describe the hardware used to run its experiments. The ethics statement explicitly states: 'Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [No] The computation is not intensive and therefore we do not see the need to specify the details.' |
| Software Dependencies | No | The paper does not provide a reproducible description of ancillary software, specifically lacking version numbers for key software components or self-contained solvers. |
| Experiment Setup | Yes | Let {bηk} b K k=1 be the output of the NBS algorithm, with inputs: ... tuning parameter τ satisfying c1n log3/2(T) < τ < c2κ2 0n2ρ2 α2, where c1, c2 > 0 are absolute constants. ... random intervals whose end points are drawn independently and uniformly from {1, . . . , T} such that max M m=1(βm αm) CR , for some constant CR > 3/2 |