PRI-VAE learns disentangled representations by optimizing principle-of-relevant-information.
problem Learning disentangled representations under VAE framework remains unknown.
method Proposes PRI-VAE, a novel learning objective to optimize disentanglement.
result Demonstrates effectiveness of PRI-VAE on four benchmark datasets.
We extend Stochastic Gradient Variational Bayes to perform posterior inference for the weights of Stick-Breaking processes. This development allows us to define a Stick-Breaking Variational Autoencoder (SB-VAE), a Bayesian nonparametric version of the variational autoencoder that has a latent representation with stocha…
Study reveals the regularization effect of variational distributions in VAEs.
problem Understanding the regularization role of variational distributions in VAEs.
method Analyzed the role of variational family in VAEs and studied the regularization effect on local geometry.
result Uncovered the implicit regularizer in the β-VAE objective and proposed a deterministic autoencoding objective. ED-VAE improves VAEs by explicitly including entropy components in ELBO.
problem Limitations of traditional VAEs with ELBO in generating high-quality samples and interpreting latent spaces.
method Introduces ED-VAE, a re-formulation of ELBO that includes entropy and cross-entropy components.
result Significantly enhances model flexibility and improves interpretability and generative performance.
This work tackles posterior collapse in conditional and hierarchical VAEs.
problem Posterior collapse in VAEs leads to poor latent variable representations.
method Theoretical analysis of linear conditional and hierarchical VAEs, empirical validation.
result Theoretical and empirical evidence of posterior collapse causes in conditional and hierarchical VAEs.
DAEs can generate images without additional loss terms, inheriting VAE properties.
problem Difficulty in using VAEs for practical generative modelling.
method Empirical exploration of DAEs for image generation without novel methods.
result DAEs can generate images successfully without additional loss terms.
The paper provides convergence guarantees for VAEs using SGD and Adam.
problem Understanding theoretical convergence guarantees for VAEs.
method Derives non-asymptotic convergence rates for VAEs trained with SGD and Adam.
result Convergence rate of \(\mathcal{O}(\log n / \sqrt{n})\) with explicit hyperparameter dependencies.
In this paper, we provide an information-theoretic interpretation of the Vector Quantized-Variational Autoencoder (VQ-VAE). We show that the loss function of the original VQ-VAE can be derived from the variational deterministic information bottleneck (VDIB) principle. On the other hand, the VQ-VAE trained by the Expect…
tvGP-VAE models tensor-valued latent variables with Gaussian processes for better data structure representation.
problem Agnostic latent variables in VAEs ignore data structure correlations.
method Proposes tensor-variate Gaussian process prior for variational autoencoder.
result Explicitly modeling correlation structures improves model performance in reconstruction.
NE-VAE prevents posterior collapse in VAEs by embedding neighbors in latent space.
problem Posterior collapse in VAEs when strong decoders are used.
method Neighbor embedding in latent space to prevent collapse.
result NE-VAE produces qualitatively different latent representations with active latent dimensions.
Study shows how to manipulate VAEs for attacks and assess their robustness.
problem Adversarial attacks on Variational Autoencoders (VAE).
method Examine modifications to VAEs and propose metrics for robustness.
result Metrics to quantify the robustness of VAEs to adversarial attacks.
Lower bound for VAE training objective for binary data.
problem Finding a lower bound for the ELBO of Bernoulli VAE.
method Interpretable lower bound, modified initialization, faster training architecture, PCA for latent space dimension.
result Theoretical result and improved performance of new architecture.
We present two deep generative models based on Variational Autoencoders to improve the accuracy of drug response prediction. Our models, Perturbation Variational Autoencoder and its semi-supervised extension, Drug Response Variational Autoencoder (Dr.VAE), learn latent representation of the underlying gene states befor…
CoVAE improves VAEs by reducing training steps and improving quality.
problem Two-stage training overhead and increased sampling times.
method Consistency training of VAEs with progressive latent representations and time-dependent β parameter.
result CoVAE generates high-quality samples in one or few steps.
This work gives an in-depth derivation of the trainable evidence lower bound obtained from the marginal joint log-Likelihood with the goal of training a Multi-Modal Variational Autoencoder (M2VAE).
The variational autoencoder (VAE) is a generative model with continuous latent variables where a pair of probabilistic encoder (bottom-up) and decoder (top-down) is jointly learned by stochastic gradient variational Bayes. We first elaborate Gaussian VAE, approximating the local covariance matrix of the decoder as an o…
Proposes a method to learn conditional VAEs from datasets with missing covariates.
problem Learning conditional VAEs from datasets with missing covariates.
method Augments conditional VAEs with a prior distribution for missing covariates and estimates their posterior using amortised variational inference.
result The proposed method outperforms previous methods in learning conditional VAEs from non-temporal, temporal, and longitudinal datasets.
Paper uses VAEs to detect radar targets in complex noise.
problem Detecting radar targets in compound clutter and thermal noise.
method Proposes a VAE architecture to distinguish radar targets from various noise types.
result The VAE outperforms classical detectors in challenging noise conditions.
New methods improve genetic studies of complex diseases.
problem Improving genetic studies of complex diseases using high-dimensional clinical data.
method Evaluation of unsupervised disentangled representation learning methods (autoencoders, VAE, beta-VAE, FactorVAE) for genetic association studies.
result FactorVAEs and beta-VAEs outperform standard VAEs and non-variational autoencoders in genetic studies of asthma and COPD.
This work provides statistical guarantees for VAEs using PAC-Bayesian theory.
problem Theoretical properties of VAEs remain open questions.
method PAC-Bayesian theory to derive statistical guarantees.
result Upper bounds on Wasserstein distance between input and generative model.
GD-VAEs learn dynamics from observations using geometric and topological information.
problem Learning parsimonious representations of nonlinear dynamics from observations.
method Develops data-driven methods incorporating geometric and topological information using Variational Autoencoders (VAEs).
result GD-VAEs provide methods for learning reduced dimensional representations of nonlinear dynamics.
Certifiably robust VAEs are trained with bounds on input perturbations.
problem Ensuring VAEs are robust to adversarial attacks.
method Derive bounds on minimal perturbation size, control parameters, and train VAEs to meet criteria.
result Certifiably robust VAEs are more robust to attacks than standard VAEs.
Improved VAE estimation from incomplete data using variational mixtures.
problem Estimating VAEs from incomplete data increases posterior complexity.
method Introducing variational mixtures based on finite and imputation distributions.
result Variational mixtures improve VAE estimation accuracy from incomplete data.
This work improves VAEs using MCMC methods for better variational bounds.
problem Improving the expressiveness of variational distributions in VAEs.
method Entropy-based adaptation for MALA/HMC chains to optimize tighter variational bounds.
result Higher held-out log-likelihoods and improved generative metrics.
VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we would like to take into account at generation time. We propose in this paper GLSR-V…
InVA models image outcomes from multiple modalities, outperforming standard VAEs.
problem Understanding relationships across multiple imaging modalities in neuroimaging.
method Integrative Variational Autoencoder (InVA) framework for image-on-image regression.
result InVA accurately predicts PET scans from structural MRI, outperforming conventional models.
New GP-VAE model improves scalability and performance.
problem Inability of conventional VAEs to model correlations between data points.
method Principled sparse inference approaches to improve scalability of GP-VAEs.
result New model outperforms existing approaches in runtime and memory usage.
In just three years, Variational Autoencoders (VAEs) have emerged as one of the most popular approaches to unsupervised learning of complicated distributions. VAEs are appealing because they are built on top of standard function approximators (neural networks), and can be trained with stochastic gradient descent. VAEs …
C-VAE improves VAE by resolving prior issues and generating better samples.
problem Low-quality samples from VAE due to prior issues.
method Formulates VAE as OT, allows flexible priors, and uses OT formulations.
result C-VAE generates higher quality samples and latent representations.
The paper presents the application of Variational Autoencoders (VAE) for data dimensionality reduction and explorative analysis of mass spectrometry imaging data (MSI). The results confirm that VAEs are capable of detecting the patterns associated with the different tissue sub-types with performance than standard appro…
This paper bridges statistical and machine learning approaches to variational inference.
problem Statisticians struggle to understand variational inference from a Frequentist perspective.
method Explains VI, VAEs, and DDMs from a Frequentist viewpoint, starting with EM.
result VI emerges as a scalable solution for intractable E-steps in VAEs and DDMs.
VAEs analyzed using harmonic analysis, showing how variance controls frequency content and robustness.
problem Understanding and optimizing VAEs for robustness and frequency control.
method Viewing VAE latent space as Gaussian space, deriving results on variance and frequency content, and demonstrating soft Lipschitz constraints.
result Increasing encoder variance reduces high frequency content and improves adversarial robustness.
Score matching fails to train VAEs robustly, revealing autoencoding loss insights.
problem Catastrophic failure of variational score matching on VAE models.
method Analysis of existing variational score matching objectives and their equivalence to autoencoding losses.
result Score matching methods fail to produce robust VAE models, predicting poor performance.
Proposes a multi-view VAE for imputing missing data from correlated sources.
problem Imputing missing data from multi-view sources with latent space correlation.
method Enforces a joint prior with latent space correlation between VAEs trained on each view.
result More strongly correlated latent spaces are uncovered, enabling effective imputation.
Proposes a new VAE framework for anomaly detection in time series data.
problem Data scarcity leads to latent holes and discontinuous regions in latent space, causing non-robust reconstructions.
method Combines VAEs with self-supervised learning to address data scarcity and improve anomaly detection.
result Improves robustness of anomaly detection in time series data by addressing latent holes and discontinuities.
Bidirectional VAE reduces parameters and improves image tasks.
problem Improving image reconstruction, classification, interpolation, and generation.
method Uses a single neural network for both encoding and decoding in both forward and backward directions.
result Bidirectional VAEs reduce parameters by almost 50% and slightly outperform unidirectional VAEs.
New VAE model improves data fitting without sacrificing computational efficiency.
problem Limitation of Gaussian assumption in VAE for continuous variable fitting.
method Infinite mixture of asymmetric Laplace distribution in decoder, nonparametric M-estimator for quantile estimation.
result Model demonstrates superior data privacy adjustment and better distribution fitting.
PH-VAE models heavy-tailed data with flexible Phase-Type distributions.
problem Standard VAEs fail to capture heavy-tailed behavior in real-world data.
method PH-VAE uses Phase-Type distributions defined by continuous-time Markov chains to adaptively model tail behavior.
result PH-VAE significantly outperforms existing heavy-tail-aware VAEs in approximating diverse heavy-tailed distributions.
RTVAE uses β-divergence to detect anomalies in tabular data robustly.
problem Outliers in tabular data affect VAE training and anomaly detection.
method Robust VAE with β-divergence for mixed categorical and continuous features.
result Demonstrates effectiveness on network traffic anomaly detection.
Machine learning methods often need a large amount of labeled training data. Since the training data is assumed to be the ground truth, outliers can severely degrade learned representations and performance of trained models. Here we apply concepts from robust statistics to derive a novel variational autoencoder that is…
Develops a new robustness criterion for VAEs and provides theoretical guarantees.
problem Lack of formalization for robustness in VAEs.
method Introduces r-robustness criterion and derives reconstruction margins. result Derives theoretical guarantees for VAE robustness.
JoVA combines two VAEs to learn user and item representations for better recommendation.
problem Collaborative filtering with implicit feedback.
method Joint Variational Autoencoders (JoVA) with a hinge-based pairwise loss function (JoVA-Hinge).
result JoVA-Hinge outperforms state-of-the-art methods in top-k recommendation.
Proposes a framework to maximize mutual information in VAE models for better latent code representation.
problem Lack of explicit measurement of the quality of learned representations in VAE models.
method Variational Mutual Information Maximization Framework for VAE.
result Maximizes mutual information between latent codes and observations, improving latent code representation.
A framework connects VAEs to GLMs for better model initialization and performance.
problem Understanding and optimizing loss function critical points in VAEs.
method Introducing a theoretical framework based on GLM and EDFs.
result Maximum likelihood initialization improves VAE performance.
In Bayesian machine learning, the posterior distribution is typically computationally intractable, hence variational inference is often required. In this approach, an evidence lower bound on the log likelihood of data is maximized during training. Variational Autoencoders (VAE) are one important example where variation…
FastGAE scales graph AE and VAE to large graphs with millions of nodes.
problem Scalability issues in graph AE and VAE.
method Stochastic subgraph decoding scheme to speed up training.
result Outperforms existing approaches on various real-world graphs.
X-VAE uses data-adaptive Gaussian priors to improve latent space modeling.
problem Limitations of standard Gaussian priors in complex datasets.
method Data-adaptive Gaussian prior derived from pretrained autoencoder latent codes.
result Improved latent space modeling and generation quality.
Simplifies VAE for anomaly detection using rate-distortion theory.
problem Anomaly detection in unsupervised learning systems.
method Revisit VAE from information theory, incorporate model uncertainty.
result Competitive performance on benchmark datasets.