# Quantization-Based Regularization for Autoencoders

## TL;DR

This paper proposes a novel quantization-based regularizer for autoencoders that improves the quality of learned latent representations by combining vector quantization and Bayesian estimation techniques.

## Contribution

It introduces a Bayesian estimator-based regularization method at the bottleneck of autoencoders, enhancing their representation learning capabilities.

## Key findings

- Improved latent representations for supervised learning.
- Enhanced clustering performance.
- Better generalization compared to traditional autoencoders.

## Abstract

Autoencoders and their variations provide unsupervised models for learning low-dimensional representations for downstream tasks. Without proper regularization, autoencoder models are susceptible to the overfitting problem and the so-called posterior collapse phenomenon. In this paper, we introduce a quantization-based regularizer in the bottleneck stage of autoencoder models to learn meaningful latent representations. We combine both perspectives of Vector Quantized-Variational AutoEncoders (VQ-VAE) and classical denoising regularization methods of neural networks. We interpret quantizers as regularizers that constrain latent representations while fostering a similarity-preserving mapping at the encoder. Before quantization, we impose noise on the latent codes and use a Bayesian estimator to optimize the quantizer-based representation. The introduced bottleneck Bayesian estimator outputs the posterior mean of the centroids to the decoder, and thus, is performing soft quantization of the noisy latent codes. We show that our proposed regularization method results in improved latent representations for both supervised learning and clustering downstream tasks when compared to autoencoders using other bottleneck structures.