Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes
Authors: Minh Hoang, Nghia Hoang, Hai Pham, David Woodruff
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We validate our proposed method on several benchmarks with promising results supporting our theoretical analysis. |
| Researcher Affiliation | Collaboration | Quang Minh Hoang Department of Computer Science Carnegie-Mellon University Pittsburgh, PA 15213 qhoang@andrew.cmu.edu Trong Nghia Hoang MIT-IBM Watson AI Lab IBM Research Cambridge, MA 02142 nghiaht@ibm.com Hai Pham Language Technologies Institute Carnegie-Mellon University Pittsburgh, PA 15213 htpham@cs.cmu.edu David P. Woodruff Department of Computer Science Carnegie-Mellon University Pittsburgh, PA 15213 dwoodruf@cs.cmu.edu |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks with clear labels like 'Algorithm' or 'Pseudocode'. |
| Open Source Code | Yes | Our experimental code is released at https://github.com/hqminh/gp_sketch_nips. |
| Open Datasets | Yes | Datasets. This section presents our empirical studies on two real datasets: (a) the ABALONE dataset [42]... and (b) the GAS SENSOR dataset [5, 6]... |
| Dataset Splits | No | The paper mentions training data and performance metrics but does not provide specific details on how the data was split into training, validation, and test sets (e.g., percentages, counts, or cross-validation methodology). |
| Hardware Specification | Yes | All reported performances were averaged over 5 independent runs on a computing server with a Tesla K40 GPU with 12GB RAM. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library names with version numbers (e.g., Python 3.8, PyTorch 1.9). |
| Experiment Setup | No | The paper states 'The detailed parameterization of our entire algorithm7 is provided in Appendix C.' which means the specific experimental setup details are not present in the main text. |