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.
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 DLGPD model to learn dynamics from images for planning.
problem Planning in unknown, indirectly observable environments.
method Deep latent Gaussian process dynamics model trained jointly with neural networks.
result Demonstrates improved data efficiency and transfer learning.
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.
New method uses Fisher-Rao metric for non-Gaussian decoders.
problem Existing latent space geometry theory only works for Gaussian decoders.
method Pull back Fisher-Rao metric to latent space for non-Gaussian decoders.
result Achieves meaningful latent geometries for various non-Gaussian decoders.
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
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.
Deep learning is a hierarchical inference method formed by subsequent multiple layers of learning able to more efficiently describe complex relationships. In this work, Deep Gaussian Mixture Models are introduced and discussed. A Deep Gaussian Mixture model (DGMM) is a network of multiple layers of latent variables, wh…
Advances deep latent variable models for more flexible text generation.
problem Limited representation power of VAEs due to Gaussian assumptions and posterior collapse.
method Develops sample-based variational distributions and an LVM to directly match aggregated posterior to prior.
result Demonstrates improved text generation in various scenarios.
Proposes a VAE variant for ordinal content factors.
problem Isolating ordinal-valued content factors in deep latent variable models.
method Introduces a partially ordered set (poset) structure and a conditional Gaussian spacing prior model.
result Significant improvements in content-style separation over previous non-ordinal approaches.
This paper proposes a method to improve VAEs by extracting latent spaces from pre-trained diffusion models.
problem VAEs struggle with generating high-quality images due to unrealistic Gaussian assumptions.
method Optimizes an encoder to maximize marginal data log-likelihood and derives a decoder analytically.
result The method enhances VAE performance by discarding Gaussian assumptions and training a separate decoder network.
Recently, deep generative models have become increasingly popular in unsupervised anomaly detection. However, deep generative models aim at recovering the data distribution rather than detecting anomalies. Besides, deep generative models have the risk of overfitting training samples, which has disastrous effects on ano…
Novel deep Gaussian process improves predictive uncertainty.
problem Flexible probabilistic data representations with tractable inference.
method Structured Gaussian variational family with marginalisation.
result Improved accuracy and calibrated uncertainty estimates.
In this note we present a generative model of natural images consisting of a deep hierarchy of layers of latent random variables, each of which follows a new type of distribution that we call rectified Gaussian. These rectified Gaussian units allow spike-and-slab type sparsity, while retaining the differentiability nec…
LVM-GP solves PDEs with uncertainty using latent variables and Gaussian processes.
problem Uncertainty quantification in PDE solutions with noisy data.
method Combines latent variable model and Gaussian process for uncertainty-aware prediction.
result Efficiently captures functional dependencies and robust uncertainty quantification.
The paper introduces a method to probabilistically select inducing points in sparse Gaussian processes.
problem The challenge is selecting the optimal number of inducing points in sparse Gaussian processes.
method A point process prior is applied to the inducing points, and the posterior is approximated using stochastic variational inference.
result The model learns which and how many inducing points to use, leading to fewer inducing points being preferred as they become less informative.
GMVAE improves open-set classification by clustering latent representations.
problem Improving open-set classification accuracy and robustness.
method Cooperative learning of reconstruction and clustering in the latent space of a GMVAE.
result Achieved an average F1 improvement of 29.5% in open-set classification.
We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations. Our model stacks multiple latent GP layers to learn abstract representations of the state feature space, which is link…
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.
DLFM models complex systems with uncertainty, outperforming traditional methods.
problem Modeling highly nonlinear dynamical systems with robust uncertainty quantification.
method Deep latent force model (DLFM) using physics-informed kernels derived from ODEs.
result DLFM achieves comparable performance to non-physics-informed models on univariate tasks and captures dynamics in real-world data.
Variational inference is a powerful tool for approximate inference, and it has been recently applied for representation learning with deep generative models. We develop the variational Gaussian process (VGP), a Bayesian nonparametric variational family, which adapts its shape to match complex posterior distributions. T…
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.
In this paper we introduce deep Gaussian process (GP) models. Deep GPs are a deep belief network based on Gaussian process mappings. The data is modeled as the output of a multivariate GP. The inputs to that Gaussian process are then governed by another GP. A single layer model is equivalent to a standard GP or the GP …
Bayes-Factor-VAE models improve disentanglement of latent factors in data.
problem Disentangling latent factors in data using standard Gaussian priors is suboptimal.
method Introduced hierarchical Bayesian deep auto-encoder models with hyper-priors on latent variances.
result Bayes-Factor-VAEs outperform existing methods in latent disentanglement.
A new clustering model for mixed datasets combines continuous and non-continuous data.
problem Challenges in clustering mixed data due to heterogeneous variables.
method Mixed Deep Gaussian Mixture Model (MDGMM) with multilayer architecture.
result Automatic selection of model specifications and optimal number of clusters.
Our work improves VAE latent space clustering by enforcing invariant and equivariant learning.
problem Current VAEs fail to learn invariant and equivariant clusters in latent space.
method We use a mixture model pdf like Gaussian mixtures to enforce deep, group-invariant learning and separate semantic and equivariant variables.
result Our model effectively learns to disentangle invariant and equivariant representations, improving learning rate and image recognition.
This thesis improves deep sequence models by integrating probabilistic methods for uncertainty quantification.
problem Lack of uncertainty awareness in deep sequence models limits their deployment.
method Develops approximate Bayesian inference methods for Transformers and HiPPOs, leveraging inductive biases.
result Improves predictive and generative performance of deep sequence models by incorporating probabilistic structures.
Model learns low-dimensional representation from heterogeneous data with missing values.
problem Handling high-dimensional, noisy, and missing data from clinical records.
method Latent Gaussian process with composite likelihoods and numerical quadrature.
result Improves upon existing GPLVM methods for heterogeneous data.
Deep Gaussian processes (DGPs) can model complex marginal densities as well as complex mappings. Non-Gaussian marginals are essential for modelling real-world data, and can be generated from the DGP by incorporating uncorrelated variables to the model. Previous work on DGP models has introduced noise additively and use…
A large collection of time series poses significant challenges for classical and neural forecasting approaches. Classical time series models fail to fit data well and to scale to large problems, but succeed at providing uncertainty estimates. The converse is true for deep neural networks. In this paper, we propose a hy…
Method learns model for unknown stochastic system from data.
problem Modeling unknown stochastic dynamical systems.
method Autoencoder approach using deep neural networks (DNNs).
result Decoder serves as a predictive model for unknown stochastic systems.
SIS-RNN improves model flexibility for sequential data.
problem Limited expressive power of existing stochastic RNNs.
method Semi-implicit variational inference for implicit latent representations.
result SIS-RNN outperforms existing methods in various tasks.
This research examines the geometry of latent spaces in push-forward generative models.
problem Tendency of deep generative models to output samples outside target distribution support.
method Geometric measure theory and truncation method to enforce simplicial cluster structure.
result Proves sufficient condition for optimality in latent space geometry.
Enhances topic models to better handle polysemous words.
problem Lack of polysemy handling in Gaussian latent Dirichlet allocation.
method Introduces a hierarchical structure to capture polysemy in Gaussian latent Dirichlet allocation.
result Significantly improves polysemy detection and provides more parsimonious topic representations.
VED framework learns low-dimensional latent representations of physical systems.
problem Learning latent representations of complex physical systems.
method Variational Encoder-Decoder (VED) framework with KL divergence and covariance regularization.
result VED achieves lower-dimensional latent representations with improved feature disentanglement.
A scalable deep GMRF model for general graphs improves predictions and uncertainty estimates.
problem Handling generally structured data on graphs efficiently.
method A new multi-layer structure of Deep GMRFs designed for general graphs, enabling efficient training and close-to-exact Bayesian inference.
result Close-to-exact Bayesian inference for latent field predictions with uncertainty estimates.
We propose a novel Bayesian approach to modelling nonlinear alignments of time series based on latent shared information. We apply the method to the real-world problem of finding common structure in the sensor data of wind turbines introduced by the underlying latent and turbulent wind field. The proposed model allows …
This paper improves confidence measurement in deep metric learning models.
problem Measuring confidence in deep metric learning models is challenging.
method Approximates class distributions using Gaussian kernel smoothing and calibrates the confidence metric.
result Improves generalization and robustness of deep metric learning models.
New method proves identifiability of deep generative models with algebraic contrast principles.
problem Proving identifiability of deep generative models in unsupervised learning.
method Introducing three algebraic contrast principles: domain contrast, mechanism contrast, and interaction contrast.
result Proves identifiability of deep generative models with piecewise-affine decoders and Gaussian mixture priors.
DVIP improves on IP-based methods by using IPs as priors over latent functions.
problem Limited expressiveness of IP-based models, especially in function space.
method Proposes DVIP, a multi-layer generalization of IPs, and scalable variational inference.
result DVIP outperforms previous IP-based methods and deep GPs in regression and classification tasks.
Combines boosting and latent Gaussian models for better predictions.
problem Boosting's assumptions and latent Gaussian models' limitations.
method Integrates tree-boosting and latent Gaussian models.
result Increased prediction accuracy in simulations and real-world data.
New method predicts dynamic relationships in terrorist networks.
problem Dynamic co-evolution of multiplex graphs and nodal attributes in terrorism networks.
method Time-varying stochastic latent factor models with neural network Gaussian processes.
result Superior performance in predicting unobserved dynamic relationships.
Develops a new unsupervised clustering method using Variational Information Bottleneck and Gaussian Mixture Model.
problem Unsupervised clustering of unlabeled data.
method Combines Variational Information Bottleneck and Gaussian Mixture Model in a deep neural network framework.
result Derives a new bound on the cost function and provides an algorithm for efficient computation.
Efficiently learns deep factor graphs using Gaussian belief propagation.
problem Learning in deep factor graphs with efficient inference.
method Treats all relevant quantities as random variables, uses belief propagation for inference.
result Efficiently solves training and prediction problems in deep factor graphs with belief propagation.
A new model designs molecular latent vectors for drug discovery.
problem Designing effective molecular descriptors from molecular structures.
method Proposes a denoising diffusion probabilistic model (DDPM) for variational autoencoding molecular graphs.
result Demonstrates superior prediction performance and robustness compared to existing approaches.
This paper tackles high-dimensional uncertainty quantification with semi-supervised learning.
problem High-dimensional uncertainty quantification due to the curse of dimensionality.
method Autoencoder for dimension reduction, DFN for mapping and reconstruction, GP for surrogate modeling, semi-supervised learning for accuracy.
result The framework effectively reduces uncertainty quantification and reliability analysis for high-dimensional problems.
Simple Deep LDA models achieve accuracy competitive with softmax baselines.
problem Training Deep LDA models by maximum likelihood estimation leads to overlapping or collapsed class clusters.
method Proposed a constrained Deep LDA formulation with geometric constraints to fix class means and covariance.
result MLE becomes stable under geometric constraints, yielding well-separated class clusters.
Deep models can't generate heavy-tailed samples well.
problem Understanding the limitations of deep generative models in generating samples with heavy tails.
method Unified framework using concentration of measure and convex geometry, Gromov-Levy inequality.
result Deep generative models are not universal generators and can only produce concentrated samples with light tails.