Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models
Authors: Shanshan Wu, Sujay Sanghavi, Alexandros G. Dimakis
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We provide experimental results to support our analysis. and 4 Experiments In both of the simulations below, the external field is set to be zero. Sampling is done via exactly computing the distribution. We implement the algorithm in Matlab. All experiments are done using a personal desktop. |
| Researcher Affiliation | Academia | Shanshan Wu, Sujay Sanghavi, Alexandros G. Dimakis Department of Electrical and Computer Engineering University of Texas at Austin shanshan@utexas.edu, sanghavi@mail.utexas.edu, dimakis@austin.utexas.edu |
| Pseudocode | Yes | Algorithm 1: Learning an Ising model via ℓ1-constrained logistic regression and Algorithm 2: Learning a pairwise graphical model via ℓ2,1-constrained logistic regression |
| Open Source Code | Yes | Source code can be found at https://github.com/wushanshan/Graph Learn. |
| Open Datasets | No | In both of the simulations below, the external field is set to be zero. Sampling is done via exactly computing the distribution. The paper describes data generation through simulation rather than using pre-existing public datasets, and thus provides no access information for a public dataset. |
| Dataset Splits | No | The paper does not provide specific details on dataset splits (e.g., percentages, sample counts, or references to standard splits) for training, validation, or testing. |
| Hardware Specification | No | All experiments are done using a personal desktop. This statement lacks specific details about the hardware components (e.g., CPU, GPU models, memory size) used for the experiments. |
| Software Dependencies | No | We implement the algorithm in Matlab. The paper mentions the software used (Matlab) but does not provide a specific version number or other software dependencies with their versions. |
| Experiment Setup | Yes | In both of the simulations below, the external field is set to be zero. Sampling is done via exactly computing the distribution. We implement the algorithm in Matlab. All experiments are done using a personal desktop. and For each value of k, we simulate both algorithms 100 runs, and in each run we generate random Wij matrices with entries 0.2. |