Experienced Optimization with Reusable Directional Model for Hyper-Parameter Search
Authors: Yi-Qi Hu, Yang Yu, Zhi-Hua Zhou
IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | conduct experiments on learning the hyper-parameters of heterogeneous ensembles and neural network architectures. Experimental results verify that the proposed approach can significantly improve the learning accuracy within a limited hyper-parameter sample budget. |
| Researcher Affiliation | Academia | Yi-Qi Hu, Yang Yu, Zhi-Hua Zhou National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China {huyq, yuy, zhouzh}@lamda.nju.edu.cn |
| Pseudocode | Yes | Algorithm 1: Framework of Experienced Optimization by Directional Model, Algorithm 2: Experienced SRACOS (EXPSRACOS) |
| Open Source Code | Yes | An implementation of EXPSRACOS can be found at https: //github.com/eyounx/Exp SRacos. |
| Open Datasets | Yes | We collected 34 UCI classification datasets. Among these, 24 datasets are the source datasets... We use two image datasets: MNIST [Le Cun et al., 1998] as the source dataset and SVHN [Netzer et al., 2011] as the target dataset. |
| Dataset Splits | Yes | Taking k-fold cross validation as the evaluation criterion of Cδ, the evaluation can be formulated as follows: i=1 L(Cδ, Di train, Di valid), where L( ) is a loss function, Di train and Di valid are the training and validation data in the i-th fold. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU/CPU models or memory specifications used for running the experiments. |
| Software Dependencies | No | The paper mentions that its codes are based on 'scikit-learn [Pedregosa et al., 2011]' but does not specify a version number for this or any other software dependency. |
| Experiment Setup | Yes | For organizing the experience dataset, SRACOS has 200 evaluation budget and repeat for 10 times. We set 50 sample budget for all the compared methods. We use Adam as the optimizer, and its learning rate is also an important hyper-parameter. We separately set optimization epoch size is 20 and 30 for all training in MNIST and SVHN. The sample budget is set to 200, and optimization process is repeated for 5 times independently. |