FONDUE: an Algorithm to Find the Optimal Dimensionality of the Latent Representations of Variational Autoencoders

Lisa Bonheme, Marek Grzes

Keywords: variational autoencoders, VAEs, representation learning, intrinsic dimension estimation, IDE, polarised regime

TL;DR: A principled method using intrinsic dimension estimation to find the optimal number of latent dimensions for variational autoencoders.

Abstract:

When training a variational autoencoder (VAE) on a given dataset, determining the optimal number of latent variables is mostly done by grid search: a costly process in terms of computational time and carbon footprint.
In this paper, we explore the intrinsic dimension estimation (IDE) of the data and latent representations learned by VAEs.
We show that the discrepancies between the IDE of the mean and sampled representations of a VAE after only a few steps of training reveal the presence of passive variables in the latent space, which, in well-behaved VAEs, indicates a superfluous number of dimensions.
Using this property, we propose FONDUE: an algorithm which quickly finds the number of latent dimensions after which the mean and sampled representations start to diverge (i.e., when passive variables are introduced), providing a principled method for selecting the number of latent dimensions for VAEs and autoencoders.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Generative models

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/fondue-an-algorithm-to-find-the-optimal/code)