Beyond Diagonal Covariance: Flexible Posterior VAEs via Free-Form Injective Flows

• URL: http://arxiv.org/abs/2506.01522v1
• Date: Mon, 02 Jun 2025 10:36:27 GMT
• Title: Beyond Diagonal Covariance: Flexible Posterior VAEs via Free-Form Injective Flows
• Authors: Peter Sorrenson, Lukas Lührs, Hans Olischläger, Ullrich Köthe,
• Abstract summary: Variational Autoencoders (VAEs) are powerful generative models widely used for learning interpretable latent spaces, quantifying uncertainty, and compressing data for downstream generative tasks.<n>We show that a regularized variant of the recently introduced Free-form Injective Flow (FIF) can be interpreted as a VAE featuring a highly flexible, implicitly defined posterior.
• Score: 7.655073661577189
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Variational Autoencoders (VAEs) are powerful generative models widely used for learning interpretable latent spaces, quantifying uncertainty, and compressing data for downstream generative tasks. VAEs typically rely on diagonal Gaussian posteriors due to computational constraints. Using arguments grounded in differential geometry, we demonstrate inherent limitations in the representational capacity of diagonal covariance VAEs, as illustrated by explicit low-dimensional examples. In response, we show that a regularized variant of the recently introduced Free-form Injective Flow (FIF) can be interpreted as a VAE featuring a highly flexible, implicitly defined posterior. Crucially, this regularization yields a posterior equivalent to a full Gaussian covariance distribution, yet maintains computational costs comparable to standard diagonal covariance VAEs. Experiments on image datasets validate our approach, demonstrating that incorporating full covariance substantially improves model likelihood.

Related papers

• Hyperspherical Variational Autoencoders Using Efficient Spherical Cauchy Distribution [0.0]
  We propose a novel variational autoencoder (VAE) architecture that employs a spherical Cauchy (spCauchy) latent distribution.<n>Unlike traditional Gaussian latent spaces or the widely used von Mises-Fisher (vMF) distribution, spCauchy provides a more natural hyperspherical representation of latent variables.
  arXiv  Detail & Related papers  (2025-06-26T14:01:51Z)
• EquiReg: Equivariance Regularized Diffusion for Inverse Problems [67.01847869495558]
  We propose EquiReg diffusion, a framework for regularizing posterior sampling in diffusion-based inverse problem solvers.<n>When applied to a variety of solvers, EquiReg outperforms state-of-the-art diffusion models in both linear and nonlinear image restoration tasks.
  arXiv  Detail & Related papers  (2025-05-29T01:25:43Z)
• A Non-negative VAE:the Generalized Gamma Belief Network [49.970917207211556]
  The gamma belief network (GBN) has demonstrated its potential for uncovering multi-layer interpretable latent representations in text data. We introduce the generalized gamma belief network (Generalized GBN) in this paper, which extends the original linear generative model to a more expressive non-linear generative model. We also propose an upward-downward Weibull inference network to approximate the posterior distribution of the latent variables.
  arXiv  Detail & Related papers  (2024-08-06T18:18:37Z)
• Uniform Transformation: Refining Latent Representation in Variational Autoencoders [7.4316292428754105]
  We introduce a novel adaptable three-stage Uniform Transformation (UT) module to address irregular latent distributions. By reconfiguring irregular distributions into a uniform distribution in the latent space, our approach significantly enhances the disentanglement and interpretability of latent representations. Empirical evaluations demonstrated the efficacy of our proposed UT module in improving disentanglement metrics across benchmark datasets.
  arXiv  Detail & Related papers  (2024-07-02T21:46:23Z)
• Variational Laplace Autoencoders [53.08170674326728]
  Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. We present a novel approach that addresses the limited posterior expressiveness of fully-factorized Gaussian assumption. We also present a general framework named Variational Laplace Autoencoders (VLAEs) for training deep generative models.
  arXiv  Detail & Related papers  (2022-11-30T18:59:27Z)
• Generalised Gaussian Process Latent Variable Models (GPLVM) with Stochastic Variational Inference [9.468270453795409]
  We study the doubly formulation of the BayesianVM model amenable with minibatch training. We show how this framework is compatible with different latent variable formulations and perform experiments to compare a suite of models. We demonstrate how we can train in the presence of massively missing data and obtain high-fidelity reconstructions.
  arXiv  Detail & Related papers  (2022-02-25T21:21:51Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)
• Preventing Posterior Collapse Induced by Oversmoothing in Gaussian VAE [7.845959449872641]
  We propose AR-ELBO, which controls the smoothness of the model by adapting the variance parameter. In addition, we extend VAE with alternative parameterizations on the variance parameter to deal with non-uniform or conditional data variance. The proposed VAE extensions trained with AR-ELBO show improved Fr'echet inception distance (FID) on images generated from the MNIST and CelebA datasets.
  arXiv  Detail & Related papers  (2021-02-17T10:00:49Z)
• SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows [78.77808270452974]
  SurVAE Flows is a modular framework for composable transformations that encompasses VAEs and normalizing flows. We show that several recently proposed methods, including dequantization and augmented normalizing flows, can be expressed as SurVAE Flows.
  arXiv  Detail & Related papers  (2020-07-06T13:13:22Z)
• Disentangled Representation Learning and Generation with Manifold Optimization [10.69910379275607]
  This work presents a representation learning framework that explicitly promotes disentanglement by encouraging directions of variations. Our theoretical discussion and various experiments show that the proposed model improves over many VAE variants in terms of both generation quality and disentangled representation learning.
  arXiv  Detail & Related papers  (2020-06-12T10:00:49Z)
• tvGP-VAE: Tensor-variate Gaussian Process Prior Variational Autoencoder [0.0]
  tvGP-VAE is able to explicitly model correlation via the use of kernel functions. We show that the choice of which correlation structures to explicitly represent in the latent space has a significant impact on model performance.
  arXiv  Detail & Related papers  (2020-06-08T17:59:13Z)
• Gaussianization Flows [113.79542218282282]
  We propose a new type of normalizing flow model that enables both efficient iteration of likelihoods and efficient inversion for sample generation. Because of this guaranteed expressivity, they can capture multimodal target distributions without compromising the efficiency of sample generation.
  arXiv  Detail & Related papers  (2020-03-04T08:15:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.