Learning Energy-based Variational Latent Prior for VAEs

• URL: http://arxiv.org/abs/2510.00260v1
• Date: Tue, 30 Sep 2025 20:32:00 GMT
• Title: Learning Energy-based Variational Latent Prior for VAEs
• Authors: Debottam Dutta, Chaitanya Amballa, Zhongweiyang Xu, Yu-Lin Wei, Romit Roy Choudhury,
• Abstract summary: Variational Auto-Encoders (VAEs) are known to generate blurry and inconsistent samples.<n>A prior hole refers to regions that have high probability under the VAE's prior but low probability under the VAE's posterior.<n>This paper proposes to model the prior as an energy-based model (EBM)
• Score: 11.63676322474951
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Variational Auto-Encoders (VAEs) are known to generate blurry and inconsistent samples. One reason for this is the "prior hole" problem. A prior hole refers to regions that have high probability under the VAE's prior but low probability under the VAE's posterior. This means that during data generation, high probability samples from the prior could have low probability under the posterior, resulting in poor quality data. Ideally, a prior needs to be flexible enough to match the posterior while retaining the ability to generate samples fast. Generative models continue to address this tradeoff. This paper proposes to model the prior as an energy-based model (EBM). While EBMs are known to offer the flexibility to match posteriors (and also improving the ELBO), they are traditionally slow in sample generation due to their dependency on MCMC methods. Our key idea is to bring a variational approach to tackle the normalization constant in EBMs, thus bypassing the expensive MCMC approaches. The variational form can be approximated with a sampler network, and we show that such an approach to training priors can be formulated as an alternating optimization problem. Moreover, the same sampler reduces to an implicit variational prior during generation, providing efficient and fast sampling. We compare our Energy-based Variational Latent Prior (EVaLP) method to multiple SOTA baselines and show improvements in image generation quality, reduced prior holes, and better sampling efficiency.

Related papers

• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Bayesian full waveform inversion with sequential surrogate model refinement [0.0]
  Markov chain Monte Carlo (MCMC) methods sample posterior probability density functions.<n> Dimensionality-reduction methods can help define the prior and train surrogate models.<n>We propose an iterative method that progressively refines the surrogate model.
  arXiv  Detail & Related papers  (2025-05-06T07:17:03Z)
• Distributional Diffusion Models with Scoring Rules [83.38210785728994]
  Diffusion models generate high-quality synthetic data.<n> generating high-quality outputs requires many discretization steps.<n>We propose to accomplish sample generation by learning the posterior em distribution of clean data samples.
  arXiv  Detail & Related papers  (2025-02-04T16:59:03Z)
• Tackling the Problem of Distributional Shifts: Correcting Misspecified, High-Dimensional Data-Driven Priors for Inverse Problems [39.58317527488534]
  In astrophysical applications, it is often difficult or even impossible to acquire independent and identically distributed samples from the underlying data-generating process of interest.<n>We propose addressing this issue by iteratively updating the population-level distributions by retraining the model with posterior samples from different sets of observations.<n>We show that, starting from a misspecified prior distribution, the updated distribution becomes progressively closer to the underlying population-level distribution.
  arXiv  Detail & Related papers  (2024-07-24T22:39:27Z)
• Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood [64.95663299945171]
  Training energy-based models (EBMs) on high-dimensional data can be both challenging and time-consuming. There exists a noticeable gap in sample quality between EBMs and other generative frameworks like GANs and diffusion models. We propose cooperative diffusion recovery likelihood (CDRL), an effective approach to tractably learn and sample from a series of EBMs.
  arXiv  Detail & Related papers  (2023-09-10T22:05:24Z)
• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models [49.81937966106691]
  We develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models. In contrast to prior works, our theory is developed based on an elementary yet versatile non-asymptotic approach.
  arXiv  Detail & Related papers  (2023-06-15T16:30:08Z)
• LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders [26.349085280990657]
  We propose a latent distribution consistency approach to avoid substantial inconsistency between the posterior and prior latent distributions. Our method has achieved comparable or even better performance than several powerful improvements of VAEs.
  arXiv  Detail & Related papers  (2021-09-22T10:34:40Z)
• Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach [38.45568741734893]
  Inference in our GP model is done by a single feed forward pass through the network, significantly faster than semi-amortized methods. We show that our approach attains higher test data likelihood than the state-of-the-arts on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-02-05T13:01:12Z)
• Cauchy-Schwarz Regularized Autoencoder [68.80569889599434]
  Variational autoencoders (VAE) are a powerful and widely-used class of generative models. We introduce a new constrained objective based on the Cauchy-Schwarz divergence, which can be computed analytically for GMMs. Our objective improves upon variational auto-encoding models in density estimation, unsupervised clustering, semi-supervised learning, and face analysis.
  arXiv  Detail & Related papers  (2021-01-06T17:36:26Z)
• Learning Energy-Based Models by Diffusion Recovery Likelihood [61.069760183331745]
  We present a diffusion recovery likelihood method to tractably learn and sample from a sequence of energy-based models. After training, synthesized images can be generated by the sampling process that initializes from Gaussian white noise distribution. On unconditional CIFAR-10 our method achieves FID 9.58 and inception score 8.30, superior to the majority of GANs.
  arXiv  Detail & Related papers  (2020-12-15T07:09:02Z)
• A Contrastive Learning Approach for Training Variational Autoencoder Priors [137.62674958536712]
  Variational autoencoders (VAEs) are one of the powerful likelihood-based generative models with applications in many domains. One explanation for VAEs' poor generative quality is the prior hole problem: the prior distribution fails to match the aggregate approximate posterior. We propose an energy-based prior defined by the product of a base prior distribution and a reweighting factor, designed to bring the base closer to the aggregate posterior.
  arXiv  Detail & Related papers  (2020-10-06T17:59:02Z)

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.