Learning Some Popular Gaussian Graphical Models without Condition Number Bounds
Authors: Jonathan Kelner, Frederic Koehler, Raghu Meka, Ankur Moitra
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We ran several simulations on synthetic data (i.e. generated by a true GGM), and also a small Riboflavin dataset from [50], to compare our method to those previously proposed in the literature, including the Graphical Lasso, CLIME, ACLIME and the Lasso-based Meinhausen-Buhlmann estimator. |
| Researcher Affiliation | Academia | Jonathan Kelner MIT Frederic Koehler MIT Raghu Meka UCLA Ankur Moitra MIT |
| Pseudocode | No | The paper describes algorithms in prose and states that 'A more detailed description of the algorithm is given in the Appendix.' and 'some technical details are left to the full algorithm description given in the Appendix', but no pseudocode or algorithm block is present in the provided text. |
| Open Source Code | No | The paper does not provide any concrete access to source code for the methodology described, nor does it explicitly state that the code is being released. |
| Open Datasets | Yes | We ran several simulations on synthetic data (i.e. generated by a true GGM), and also a small Riboflavin dataset from [50] |
| Dataset Splits | No | The paper mentions using synthetic data and a specific dataset but does not provide specific details on training, validation, or test splits, such as percentages, sample counts, or the methodology for creating these splits. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU or CPU models, memory, or types of computing resources used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific details on ancillary software, such as library or solver names with version numbers, needed to replicate the experiments. |
| Experiment Setup | Yes | We propose the following simple algorithm and show that it succeeds in learning the graph structure of attractive GGMs. This algorithm, called GREEDYANDPRUNE, does the following to learn the neighborhood of node i: 1. Set S = and let ν > 0 be a thresholding parameter. |