Distribution Free Domain Generalization
Authors: Peifeng Tong, Wu Su, He Li, Jialin Ding, Zhan Haoxiang, Song Xi Chen
ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The DFDG is shown to offer a superior performance in empirical studies with fewer hyperparameters, which means faster and easier implementation. |
| Researcher Affiliation | Academia | 1Guanghua School of Management, Peking University, Beijing 100871, China 2Center for Big Data Research, Peking University, Beijing 100871, China 3School of Mathematical Science, Peking University, Beijing 100871, China 4Pazhou Lab, Guangzhou 510330, China. |
| Pseudocode | Yes | Algorithm 1: Distribution free domain generalization |
| Open Source Code | Yes | Further technical details, proofs and the example codes are available with this paper at https://github.com/t ongpf/Distribution-Free-Domain-General ization. |
| Open Datasets | Yes | The Office+Caltech dataset (Gong et al., 2012) consists of 2533 images from ten classes over four domains... The VLCS dataset (Fang et al., 2013) consists of four domains... The Terra Incognita data (Beery et al., 2018) were acquired from the Domain Bed dataset (Gulrajani & Lopez-Paz, 2021)... |
| Dataset Splits | Yes | The hyperparameters were selected by the grid search in the validation set, where 30% of each source domain was chosen as the validation set in the training, the so-called the training-domain validation method (Gulrajani & Lopez-Paz, 2021). |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU models, CPU types, or cloud instance specifications used for running the experiments. |
| Software Dependencies | No | The paper mentions software components like SVM, 1-NN, De CAF network, and Res Net 50, but does not provide specific version numbers for any of them. |
| Experiment Setup | Yes | Compared with the existing kernel DG methods which involve more metrics and more hyperparameters as shown in Table 2, there is only one hyperparameter γ in (10). In practice, one may add εI with ε = 10 5 for numerically stable performance so that F B = (Q + γK + εI)BΓ. The product kernel (24) was used for all the kernel-based DG methods, where k1, k2 and K are Gaussian kernels with bandwidth h, h and one, respectively. The bandwidth h is chosen by the median heuristic unless specified otherwise. |