Geometry-Preserving Encoder/Decoder in Latent Generative Models

TL;DR

This paper introduces a geometry-preserving encoder/decoder framework for latent generative models, offering theoretical convergence guarantees and improved training efficiency over traditional VAEs.

Contribution

The paper proposes a novel geometry-preserving encoder/decoder with theoretical convergence guarantees, enhancing training efficiency in latent diffusion models.

Findings

Faster convergence of decoder training with the new encoder

Theoretical proofs of convergence for encoder training

Advantages over traditional VAEs in preserving data geometry

Abstract

Generative modeling aims to generate new data samples that resemble a given dataset, with diffusion models recently becoming the most popular generative model. One of the main challenges of diffusion models is solving the problem in the input space, which tends to be very high-dimensional. Recently, solving diffusion models in the latent space through an encoder that maps from the data space to a lower-dimensional latent space has been considered to make the training process more efficient and has shown state-of-the-art results. The variational autoencoder (VAE) is the most commonly used encoder/decoder framework in this domain, known for its ability to learn latent representations and generate data samples. In this paper, we introduce a novel encoder/decoder framework with theoretical properties distinct from those of the VAE, specifically designed to preserve the geometric structure of the data distribution. We demonstrate the significant advantages of this geometry-preserving encoder in the training process of both the encoder and decoder. Additionally, we provide theoretical results proving convergence of the training process, including convergence guarantees for encoder training, and results showing faster convergence of decoder training when using the geometry-preserving encoder.