Tutorial on combining latent variable models with deep learning.
problem Combining latent variable models with deep learning to model natural language.
method Exploring variational inference to address intractable posterior inference and non-differentiability issues.
result Exploration of variational inference techniques to handle deep latent variable models.
Proposes a deep latent factor model for better recommendation systems.
problem Improving collaborative filtering in recommendation systems.
method Introduces a deeper latent factor model using deep learning.
result Significantly outperforms state-of-the-art techniques in experiments.
New method identifies latent relationships in deep models without additional constraints.
problem Latent representations in deep latent variable models are not statistically identifiable.
method Identifies relationships between latent variables (distances, angles, volumes) under mild model conditions.
result Empirically demonstrates more reliable latent distances without additional labeled data.
This work proposes a new method to train models with deep latent hierarchies using Optimal Transport.
problem Training models with deep latent hierarchies using VAEs often leads to the 'latent variable collapse' issue.
method Proposes a novel approach based on Optimal Transport to train models with deep latent hierarchies.
result The method avoids the 'latent variable collapse' issue and provides better sample generations and latent representation.
Variational autoencoders learn deep latent models.
problem Learning deep latent-variable models.
method Principled framework using variational inference.
result Introduction to variational autoencoders and extensions.
Investigates latent variable models for useful generative concept representations.
problem Creating latent representations that support various concepts and attributes.
method Latent variable modeling, including latent variable models, latent representations, and latent spaces.
result Hierarchical latent representations and latent space vectors and geometry are effective for generative concept representations.
Deep Discrete Encoders (DDEs) tackle interpretable generative models for rich data with discrete latent layers.
problem Overparametrized, non-identifiable, and uninterpretable deep generative models in high-stakes applications.
method Directed graphical model with multiple binary latent layers, transparent identifiability conditions, scalable estimation pipeline.
result Transparent identifiability conditions and scalable estimation pipeline for interpretable DDEs.
Proposes a non-parametric method for deep discrete latent variable models.
problem Learning sparse discrete latent representations in deep models.
method Iterative algorithm with Beta-Bernoulli process prior and local data scaling.
result Improves sparsity and scalability of deep discrete latent variable models.
Deep model learns complex latent codes without assuming factor structure.
problem Learning latent codes with complex, non-factorial distributions.
method Deep generative factor analysis with beta process prior and stochastic EM algorithm.
result Preliminary results show model can approximate complex distributions.
Deep equilibrium models estimate latent variables from data.
problem Estimating latent variables from data.
method Generalized exponential family models, deep equilibrium networks.
result Deep equilibrium models solve MAP estimates for latent and transformation parameters.
Geodesic clustering improves latent space clustering in deep generative models.
problem Latent representations in deep generative models distort semantic distances, making clustering difficult.
method Proposed an efficient algorithm for computing geodesics and distances in the latent space, accounting for its distortion.
result Geodesic distance reflects the internal structure of the data, improving clustering performance.
Refines deep generative models to improve data density precision.
problem Achieving precise representation of data probability density in deep models.
method Iterated generative modeling to refine latent space, addressing topological obstructions.
result Latent Space Refinement (LaSeR) protocol improves generative model precision.
Deep latent variable models are powerful tools for representation learning. In this paper, we adopt the deep information bottleneck model, identify its shortcomings and propose a model that circumvents them. To this end, we apply a copula transformation which, by restoring the invariance properties of the information b…
Improved DSSMs for easier interpretable latent variables.
problem Complex and hard-to-interpret latent variables in DSSMs.
method Simplified predictive decoder and shrinkage priors.
result Interpretable latent variables improve forecasting performance.
Ensemble decoders to capture latent space topology in deep generative models.
problem Topological mismatch between latent space geometry and data manifolds.
method Using ensembles of decoders to compute geodesics on the expected manifold.
result Ensemble approach provides a simple and reliable way to capture model uncertainty in latent space.
Proposes a deep probabilistic multi-view model for multi-view learning.
problem Learning from multiple related views with shared latent structure.
method Probabilistic Canonical Correlation Analysis (CCA) in latent space, deep generative networks, variational inference.
result Efficient variational inference approximates posterior distributions of latent multi-view layer.
Enhances deep kernel learning with stochastic latent variables for better model regularization.
problem Weak model regularization in deep kernel learning, especially on small datasets.
method Introduces DLVKL model with stochastic latent variables, NSDE for expressive posterior, and hybrid prior.
result DLVKL-NSDE outperforms existing deep GPs on large datasets.
Proposes SQUAD for better predictive uncertainty in deep latent models.
problem Intractable inference in deep latent variable models lead to overconfident predictions.
method Introduces Stochastic Quantized Activation Distributions (SQUAD) for flexible yet tractable latent variable distributions.
result The model provides competitive quality predictive uncertainty and learns non-linearities.
Study shows latent space OOD detection isn't a reliable proxy for model performance.
problem Evaluating and interpreting deep learning systems on real-world data.
method Empirical investigation of latent space OOD detection and classification accuracy using SAR datasets.
result OOD detection cannot be used as a proxy measure for model performance.
New method learns latent structures for deep NLP models without tradeoffs.
problem Joint learning of latent structures and downstream predictors with end-to-end differentiability.
method SparseMAP inference for joint learning of latent structures and downstream predictors.
result First method to enable unrestricted dynamic computation graph construction from global latent structure while maintaining differentiability.
ODE2VAE learns latent dynamics for sequential data.
problem Learning latent dynamics for high-dimensional sequential data.
method Deep generative second order ODE model with Bayesian neural networks.
result State-of-the-art performance in long-term motion prediction and imputation.
Method evaluates disentanglement in DLVMs, including those not aligned with latent axes.
problem Evaluate disentanglement in DLVMs, especially those not aligned with latent axes.
method Proposes a statistical method to discover generative factors of a dataset.
result Empirically demonstrates the advantage of the method on two datasets.
SLAC learns latent representations for image-based RL tasks.
problem Challenges in learning policies from high-dimensional image observations.
method SLAC separates representation learning and task learning, using a latent variable model.
result SLAC outperforms model-free and model-based methods in image-based control tasks.
Paper presents a reparameterized DP-DLGMM for clustering.
problem Non-parametric DP priors in DLGMM are hard to couple with variational inference.
method Closed-form updates for DP-DLGMM's variational posterior.
result Model generates realistic samples and performs competitively in semi-supervised settings.
SDREM models complex network data with deep learning, improving link prediction.
problem Modeling latent structures in relational data with high-order node dependence.
method Scalable deep generative relational model (SDREM) incorporating high-order neighbourhood structure and novel data augmentation.
result Improved link prediction performance on real-world datasets.
The paper proposes a deep generative model for complex disease trajectories.
problem Modeling and analyzing complex disease trajectories.
method Deep generative time series approach with semi-supervised latent processes.
result The model can discover novel aspects of diseases and cluster them into new sub-types.
This research enhances exploration in DDPG using latent trajectory optimization.
problem Limited exploration in DDPG with deterministic policies.
method Model-based trajectory optimization for exploration in DDPG, using a learned deep dynamics model.
result Improved performance in continuous control tasks, especially with sparse rewards and images.
Moment Pooling reduces latent space dimensions in machine learning models.
problem High-dimensional latent spaces in machine learning models are hard to interpret.
method Moment Pooling extends Deep Sets networks to arbitrary multivariate moments.
result Latent dimensions as small as 1 can achieve similar performance to higher dimensions.
Our method enforces latent independence in deep generative models using a hyperprior.
problem Unsupervised disentanglement of latent representations in deep models.
method We augment VAE with an inverse-Wishart prior to enforce statistical independence in latent dimensions.
result Our approach outperforms state-of-the-art methods in disentanglement and reconstruction.
Langevin autoencoders improve deep latent variable models with efficient posterior sampling.
problem Efficient posterior sampling in deep latent variable models using MCMC.
method Amortized Langevin dynamics (ALD) replaces datapoint-wise sampling with encoder updates.
result ALD is valid as an MCMC algorithm with the target posterior as a stationary distribution.
A recurring problem when building probabilistic latent variable models is regularization and model selection, for instance, the choice of the dimensionality of the latent space. In the context of belief networks with latent variables, this problem has been adressed with Automatic Relevance Determination (ARD) employing…
New findings suggest latent regularization is unnecessary for high-quality image generation.
problem Improving image generation quality without latent regularization.
method Investigated the effect of latent regularization on image generation using learned priors.
result In the case of a sufficiently expressive prior, latent regularization is not necessary and may harm image quality.
Combines deep state space models with diffusion models for better forecasting and capturing latent dynamics
problem Forecasting and capturing latent dynamics in time series
method DDSSM: Diffusion-driven state space model
result Empirically outperforms state-of-the-art deep SSM
New method uses cycle consistency to enforce invariance in latent space.
problem Learning meaningful and independent factors of variation in datasets.
method Two separate latent subspaces, cycle consistency constraints, deep information bottleneck.
result Identifies more meaningful factors leading to sparser and interpretable models.
DICCA maps multi-view data into a shared latent space with interpretable components.
problem Learning from multiple related but distinct data views.
method DICCA extends CCA to deep generative networks and uses sparsity-inducing priors for interpretability.
result DICCA effectively disentangles shared and view-specific variations in multi-view data.
New models learn stable latent clusters without side info.
problem Stability of non-linear ICA representations without side information.
method Deep generative models with latent clusterings, compared to standard VAEs and auxiliary labeled models.
result Deep generative models with latent clusterings are as stable as models with side information.
Model learns cancer tissue images onto a low-dimensional space revealing tissue characteristics.
problem Improving cancer diagnosis through high-fidelity digital pathology.
method Deep generative model using PathologyGAN to map real images onto a latent space.
result Latent space encodes morphological characteristics and reveals distinct tissue clusters.
Deep generative models provide a systematic way to learn nonlinear data distributions, through a set of latent variables and a nonlinear "generator" function that maps latent points into the input space. The nonlinearity of the generator imply that the latent space gives a distorted view of the input space. Under mild …
Physics-guided model improves deep learning for nonlinear systems.
problem Intractable inference of nonlinear dynamical systems from data.
method Physics-guided Deep Markov Model (PgDMM) using neural networks.
result Improved performance on nonlinear systems with structured latent space.
Proposes a method to train deep models with one-element batches.
problem Training deep models with small batches (one element) is challenging.
method Splits the batch into historical and current elements for training.
result Allows training on higher resolution images with one-element batches.
Proposes a new prior for deep generative models to capture latent properties.
problem Complex non-linear relationships between data and latent properties.
method Factorial mixture prior with Gaussian mixture models for quantization.
result Empirically evaluated method for learning discrete properties in unsupervised or semi-supervised settings.
DPGDS models sequential count data with deep hierarchical structure and temporal dependencies.
problem Modeling sequentially observed multivariate count data with hierarchical and temporal dependencies.
method Developed deep Poisson-gamma dynamical systems with data augmentation and MCMC inference.
result Demonstrated excellent predictive performance and interpretable latent structure.
This research explores neural SDEs as deep latent Gaussian models in the diffusion limit.
problem Deep latent Gaussian models with time-inhomogeneous Markov chains and Gaussian perturbations.
method Develops variational inference for neural SDEs using stochastic automatic differentiation in Wiener space.
result The limiting latent object is an Itô diffusion process governed by neural nets.
Proposes a new model for directed graphs combining deep learning and latent variable models.
problem Graph representation learning for directed graphs.
method Deep Latent Space Model (DLSM) integrating GCN encoder and stochastic decoder with hierarchical variational auto-encoder architecture.
result Achieves state-of-the-art performance on link prediction and community detection tasks.
Generative model for SSc disease trajectories using deep learning.
problem Modeling complex disease trajectories in Systemic Sclerosis.
method Semi-supervised deep generative model with latent temporal processes.
result Learned latent processes enable personalized monitoring and prediction.
This paper reviews deep learning methods for state space models.
problem Analyzing temporal dynamics in dynamical systems.
method Selective review of deep neural network approaches for state space models.
result Unified perspective on discrete and continuous time SSMs.
DGPs learn from multiple tasks using shared and private latent processes.
problem Improving learning performance and information transfer between tasks.
method Non-linear mixtures of latent processes with shared and task-specific components, using hard or soft sharing.
result DGPs outperform other multi-task learning models across various settings.
Paper proposes a fast method for learning deep latent variable models.
problem Learning deep generative models with hierarchical latent variables.
method Noise initialized short run MCMC with variational optimization of step size.
result The method outperforms VAE in reconstruction and synthesis quality.