Üretken modellerde boyutsallik ve mimari uzerine analiz

Deep generative models are powerful class of machine learning models. How- ever, a significant amount of computing power and technical knowledge is required to conduct the training process. Even searching for hyperparameters requires a high com- putational cost. Moreover, there is still ongoing research on methods for evaluating generative models, and owing to the lack of a robust and consistent metric, there are limited comparisons between generative model architectures and algorithms. In this study, we attempted to compare two types of generative model architectures, Gener- ative Adversarial Networks (GANs) and Real-valued Non-Volume-Preserving (NVP) flows, with synthetic datasets as well as with a well known image dataset MNIST. We evaluate their data capturing ability according to data dimensionality and variability. We propose an Minimum Description Length (MDL) based metric to examine the ef- fect of model complexity which is measured as model's parameter count. We provide estimated Kullback-Leibler (KL) divergence and propsed MDL-based metric results. Our findings indicate that NVP models have the capability to encode more data variability while utilizing fewer parameters when contrasted with GANs for lower di- mensional datasets. The proposed MDL-based metric, facilitates selecting suitable architecture in terms of model complexity for a given dataset considering its variability and dimensionality.