For any fixed nonconstant teacher T, the best constant student has alignment cost exactly equal to the teacher mutual information I_T(X;T); a latent-only witness below this threshold with margin cannot be constant.
Deep unsupervised clustering with Gaussian mixture variational autoencoders
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models. We observe that the known problem of over-regularisation that has been shown to arise in regular VAEs also manifests itself in our model and leads to cluster degeneracy. We show that a heuristic called minimum information constraint that has been shown to mitigate this effect in VAEs can also be applied to improve unsupervised clustering performance with our model. Furthermore we analyse the effect of this heuristic and provide an intuition of the various processes with the help of visualizations. Finally, we demonstrate the performance of our model on synthetic data, MNIST and SVHN, showing that the obtained clusters are distinct, interpretable and result in achieving competitive performance on unsupervised clustering to the state-of-the-art results.
citation-role summary
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 7roles
dataset 1polarities
use dataset 1representative citing papers
PDGMM-VAE recovers latent sources in nonlinear ICA by using jointly learned per-dimension GMM priors that fit source-specific marginals and reduce permutation symmetry.
GCVAE is a variational autoencoder that structures its latent space as a Gaussian mixture and optimizes a variational objective to make the representation maximally informative about a user-chosen guiding variable, enabling context-specific clusters.
C-t³VAE introduces class-conditional Student's t priors and a gamma-power divergence objective to improve class-balanced generation in VAEs under severe imbalance.
A new aerocapture guidance method uses a probabilistic indicator function to estimate and mitigate failure risks, saving 71.43% to 100% of recoverable cases in high-uncertainty simulations across varied initial conditions and atmosphere models.
CellRefine adds a marker-gene-guided post-pretraining stage to single-cell models that refines the cell embedding manifold and improves downstream task performance by up to 15%.
GMAE learns disentangled view-specific and view-common embeddings via dual-path autoencoders and cross-view adversarial training to boost performance on complete and incomplete multi-view clustering tasks.
citing papers explorer
-
A Testable Certificate for Constant Collapse in Teacher-Guided VAEs
For any fixed nonconstant teacher T, the best constant student has alignment cost exactly equal to the teacher mutual information I_T(X;T); a latent-only witness below this threshold with margin cannot be constant.
-
PDGMM-VAE: A Variational Autoencoder with Adaptive Per-Dimension Gaussian Mixture Model Priors for Nonlinear ICA
PDGMM-VAE recovers latent sources in nonlinear ICA by using jointly learned per-dimension GMM priors that fit source-specific marginals and reduce permutation symmetry.
-
From Unsupervised to Guided Clustering: A Variational Implementation
GCVAE is a variational autoencoder that structures its latent space as a Gaussian mixture and optimizes a variational objective to make the representation maximally informative about a user-chosen guiding variable, enabling context-specific clusters.
-
Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling
C-t³VAE introduces class-conditional Student's t priors and a gamma-power divergence objective to improve class-balanced generation in VAEs under severe imbalance.
-
Risk-Aware Aerocapture Guidance Through a Probabilistic Indicator Function
A new aerocapture guidance method uses a probabilistic indicator function to estimate and mitigate failure risks, saving 71.43% to 100% of recoverable cases in high-uncertainty simulations across varied initial conditions and atmosphere models.
-
Prototype Guided Post-pretraining for Single-Cell Representation Learning
CellRefine adds a marker-gene-guided post-pretraining stage to single-cell models that refines the cell embedding manifold and improves downstream task performance by up to 15%.
-
Learning Disentangled Representations for Generalized Multi-view Clustering
GMAE learns disentangled view-specific and view-common embeddings via dual-path autoencoders and cross-view adversarial training to boost performance on complete and incomplete multi-view clustering tasks.