Adaptive Compression of the Latent Space in Variational Autoencoders
CoRR(2023)
摘要
Variational Autoencoders (VAEs) are powerful generative models that have been
widely used in various fields, including image and text generation. However,
one of the known challenges in using VAEs is the model's sensitivity to its
hyperparameters, such as the latent space size. This paper presents a simple
extension of VAEs for automatically determining the optimal latent space size
during the training process by gradually decreasing the latent size through
neuron removal and observing the model performance. The proposed method is
compared to traditional hyperparameter grid search and is shown to be
significantly faster while still achieving the best optimal dimensionality on
four image datasets. Furthermore, we show that the final performance of our
method is comparable to training on the optimal latent size from scratch, and
might thus serve as a convenient substitute.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要