Knowledge-Based Regularization in Generative Modeling
Authors: Naoya Takeishi, Yoshinobu Kawahara
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conducted experiments using multiple datasets and generative models, and the results showcase that a model regularized using prior knowledge of feature relations achieves better generalization. |
| Researcher Affiliation | Academia | Naoya Takeishi1 and Yoshinobu Kawahara2,1 1RIKEN Center for Advanced Intelligence Project 2Institute of Mathematics for Industry, Kyushu University |
| Pseudocode | Yes | Algorithm 1 Knowledge-regularized gradient method |
| Open Source Code | No | The paper does not provide any statement or link regarding the availability of open-source code for the described methodology. |
| Open Datasets | Yes | We created training and validation sets from MNIST s training dataset and a test set from MNIST s test dataset. and We used the records of solar power production1 (SOLAR) of 137 solar power plants in Alabama in June 2006. The data of the first 20 days were used for training, the next five days were for validation, and the last five days were for test. 1www.nrel.gov/grid/solar-power-data.html |
| Dataset Splits | Yes | We created training and validation sets from MNIST s training dataset and a test set from MNIST s test dataset. and The data of the first 20 days were used for training, the next five days were for validation, and the last five days were for test. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running experiments, such as GPU/CPU models or memory specifications. |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies used in the experiments. |
| Experiment Setup | Yes | Hyperparameters. We computed HSIC with m = 128 using Gaussian kernels with the bandwidth set by the median heuristics. No improvement was observed with m > 128. The hyperparameters were chosen based on the performance on the validation sets. The search was not intensive; λ was chosen from three candidate values that roughly adjust orders of L and RK, and να was chosen from .01 or .05. |