An Initial Study on the Relationship Between Meta Features of Dataset and the Initialization of NNRW

The initialization of neural networks with random weights (NNRW) has a significant impact on model performance. However, there is no suitable way to solve this problem so far. In this paper, the relationship between meta features of a dataset and the initialization of NNRW is studied. Specifically, we construct seven regression datasets with known attributes' distributions, then initialize NNRW with different distributions and trained them based on the datasets to get the corresponding models respectively. The relationship between the attributes' distributions of the datasets and the initialization of NNRW is analyzed by the performance of the models. Several interesting phenomena are observed: firstly, initializing NNRW with the Gaussian distribution can help the model to have a faster convergence rate than ones with the Gamma and Uniform distribution. Secondly, if one or more attributes in a dataset that follow the Gamma distribution, using Gamma distribution to initialize NNRW may result in a slower convergence rate and easy overfitting. Thirdly, initializing NNRW with a specific distribution with smaller variances can always achieve faster convergence rate and better generalization performance than the one with larger variances. The above experimental results are not sensitive to the activation function and the type of NNRW. Some theoretical analyses about the above observations are also given in the study.