Bootstrap Model Aggregation for Distributed Statistical Learning
Authors: JUN HAN, Qiang Liu
NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Both theoretical and empirical analysis is provided to demonstrate our methods. [...] Empirical studies are provided to verify our theoretical results and demonstrate the practical advantages of our methods. [...] We study the empirical performance of our methods on both simulated and real world datasets. |
| Researcher Affiliation | Academia | Jun Han Department of Computer Science Dartmouth College jun.han.gr@dartmouth.edu Qiang Liu Department of Computer Science Dartmouth College qiang.liu@dartmouth.edu |
| Pseudocode | Yes | Algorithm 1 KL-Control Variates Method for Combining Local Models [...] Algorithm 2 KL-Weighted Method for Combining Local Models |
| Open Source Code | No | The paper does not provide any statement about releasing source code or a link to a code repository. |
| Open Datasets | No | The paper mentions using 'Sens IT Vehicle dataset', 'Covertype', and 'Epsilon datasets' for experiments. While these are known datasets, the paper does not provide concrete access information such as direct URLs, DOIs, specific repository names, or formal citations (author names and year in brackets/parentheses) for these datasets within the provided text. |
| Dataset Splits | No | The paper does not provide specific details on training/validation/test dataset splits, such as percentages, sample counts, or citations to predefined splits. It only mentions using a 'hold-out testing dataset'. |
| Hardware Specification | No | The paper does not specify any hardware details such as GPU models, CPU types, or memory used for running experiments. |
| Software Dependencies | No | The paper mentions using 'expectation maximization (EM) to learn the parameters' but does not specify any software names with version numbers, like libraries or solvers, needed to replicate the experiment. |
| Experiment Setup | Yes | We set n = 600 and the true number of mixtures to be 10 in all the cases. [...] The number of local machines is 10 in all the cases, and the number of mixture components are taken to be the number of labels in the datasets. |