On the Shape of Latent Variables in a Denoising VAE-MoG: A Posterior Sampling-Based Study
In this work, we explore the latent space of a denoising variational autoencoder with a mixture-of-Gaussians prior (VAE-MoG), trained on gravitational wave data from event GW150914. To evaluate how well the model captures the underlying structure, we use Hamiltonian Monte Carlo (HMC) to draw posterior samples conditioned on clean inputs, and compare them to the encoder's outputs from noisy data. Although the model reconstructs signals accurately, statistical comparisons reveal a clear mismatch in the latent space. This shows that strong denoising performance doesn't necessarily mean the latent representations are reliable highlighting the importance of using posterior-based validation when evaluating generative models.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Maximum a Posteriori on a Submanifold: a General Image Restoration Method with GAN
We propose a general method for various image restoration problems, such as denoising, deblurring, super-resolution and inpainting. The problem is formulated as a constrained optimization problem. Its objective is to max…
DeblurringDenoisingDensity EstimationGenerative Adversarial Network+2Discrete flow posteriors for variational inference in discrete dynamical systems
Each training step for a variational autoencoder (VAE) requires us to sample from the approximate posterior, so we usually choose simple (e.g. factorised) approximate posteriors in which sampling is an efficient computat…
GPUVariational InferenceDiffusion Priors In Variational Autoencoders
Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling. However, VAEs are also more and more outperformed by compet…
DenoisingBayesian Deep Learning via Stochastic Gradient MCMC with a Stochastic Approximation Adaptation
We propose a robust Bayesian deep learning algorithm to infer complex posteriors with latent variables. Inspired by dropout, a popular tool for regularization and model ensemble, we assign sparse priors to the weights in…
Uncertainty QuantificationLearning Joint Latent Space EBM Prior Model for Multi-layer Generator
This paper studies the fundamental problem of learning multi-layer generator models. The multi-layer generator model builds multiple layers of latent variables as a prior model on top of the generator, which benefits lea…
Image GenerationOutlier Detection