GAR: Generalized Autoregression for Multi-Fidelity Fusion
Authors: Yuxin Wang, Zheng Xing, WEI XING
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The empirical assessment includes many canonical PDEs and real scientific examples and demonstrates that the proposed method consistently outperforms the SOTA methods with a large margin (up to 6x improvement in RMSE) with only a couple high-fidelity training samples. |
| Researcher Affiliation | Collaboration | Yuxin Wang School of Mathematical Science Beihang University Beijing, China, 100191. WYXtt_2011@163.com Zheng Xing Graphics&Computing Department Rockchip Electronics Co., Ltd Fuzhou, China, 350003 zheng.xing@rock-chips.com Wei W. Xing School of Mathematics and Statistics, University of Sheffield, Sheffield S10 2TN, UK School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China, 100191. wayne.xingle@gmail.com |
| Pseudocode | No | The paper describes algorithms and derivations but does not present them in a formal pseudocode block or algorithm environment. |
| Open Source Code | Yes | 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] Please see supplementary materials |
| Open Datasets | Yes | We test on Burger s, Poisson s and the heat equations commonly used in the literature [12, 51 53]. ... Did you use existing assets? If yes, did you cite the creators? [Yes] Please see the experimental section |
| Dataset Splits | Yes | We uniformly generate 128 samples for testing and 32 for training. We increase the high-fidelity training samples to the number of low-fidelity training samples 32. The comparisons are conducted five times with shuffled samples. |
| Hardware Specification | Yes | All experiments are run on a workstation with an AMD 5950x CPU and 32 GB RAM. |
| Software Dependencies | No | GAR, CIGAR, AR, NAR, and Res GP are implemented using Pytorch. While PyTorch is mentioned, a specific version number is not provided, which is necessary for reproducibility. |
| Experiment Setup | Yes | We uniformly generate 128 samples for testing and 32 for training. We increase the high-fidelity training samples to the number of low-fidelity training samples 32. The comparisons are conducted five times with shuffled samples. ... Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] Please see the Appendix |