Extends Gaussian Processes for multi-modal, non-stationary data.
problem Modeling non-stationary multi-modal processes.
method Adds a latent variable to modulate covariance over training data.
result Shows improved modeling of multi-modal and non-stationary processes.
GP-ALPS automatically selects latent processes for multi-output GPs.
problem Manual selection of latent processes in multi-output GPs is time-consuming and prone to biases.
method Developed a variational inference scheme to automatically choose latent processes.
result Demonstrated suitability of GP-ALPS in preliminary experiments.
A scalable factorized Gaussian process VAE for faster inference.
problem Inference bottlenecks in Gaussian process VAEs.
method Factorizes latent kernel across auxiliary features, leveraging independence.
result Significant speed-up in inference time (in theory and practice).
A new model LVMOGP captures latent conditions in supervised learning.
problem Efficiently modeling latent information in multiple conditions with few data.
method Latent Variable Multiple Output Gaussian Processes (LVMOGP) with variational inference.
result LVMOGP significantly outperforms related Gaussian process methods on various tasks.
Study improves Gaussian Process Latent Variable Model for noisy longitudinal data.
problem Noisy and incomplete longitudinal data makes learning representations difficult.
method Augment variational approximation with systematic samples of unseen observations.
result Demonstrates improved learning of Gaussian Process Dynamical Systems in noisy data.
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.
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.
Bayesian framework improves uncertainty quantification in Gaussian process models.
problem High correlations between latent variables and hyperparameters in Gaussian process models.
method Uses pseudo-marginal method to estimate marginal likelihood and explore posterior of hyperparameters.
result Demonstrates improved uncertainty quantification and multimodality in hyperparameters compared to variational inference.
TPLVM models portfolio construction for non-Gaussian financial data.
problem Optimal asset allocation in finance with non-Gaussian fluctuations.
method Student's t-process latent variable model (TPLVM) for portfolio optimization.
result TPLVM outperforms Gaussian process latent variable model in minimum-variance portfolio construction.
Study identifies influences in VAR models with latent processes.
problem Identify influences among observed and latent processes in VAR models.
method Identify support of transition matrix and lengths of latent paths.
result Support of transition matrix and lengths of latent paths can be identified successfully under certain conditions.
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.
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.
Proposes GPLFR for predicting high-dimensional outputs with few data.
problem Predicting high-dimensional outputs from limited data.
method GPLFR combines Gaussian process and linear-Gaussian decoding for high-dimensional prediction.
result GPLFR outperforms existing methods in predicting high-dimensional outputs.
This paper uses random Fourier features to simplify latent force models and convolved Gaussian processes.
problem Expensive covariance matrix calculation in latent force models due to double integrals.
method Approximates double integrals using random Fourier features to obtain simpler analytical expressions.
result Simplified analytical expressions for covariance functions, leading to faster computation.
Multi-output Gaussian processes have received increasing attention during the last few years as a natural mechanism to extend the powerful flexibility of Gaussian processes to the setup of multiple output variables. The key point here is the ability to design kernel functions that allow exploiting the correlations betw…
In a variety of disciplines such as social sciences, psychology, medicine and economics, the recorded data are considered to be noisy measurements of latent variables connected by some causal structure. This corresponds to a family of graphical models known as the structural equation model with latent variables. While …
In a variety of disciplines such as social sciences, psychology, medicine and economics, the recorded data are considered to be noisy measurements of latent variables connected by some causal structure. This corresponds to a family of graphical models known as the structural equation model with latent variables. While …
New model handles mixed data types better.
problem Handling data with different types of attributes.
method Mixed likelihood Gaussian process latent variable model with separate likelihoods for each dimension.
result Better predictive performance for real-world data with mixed attributes.
A new model family of zero-inflated Gaussian processes improves prediction and interpretability of rare event data.
problem Poor performance of conventional machine learning on zero-inflated datasets.
method Sparse kernels and latent probit Gaussian processes to zero out kernel rows and columns.
result Improves prediction of zero-inflated data and interpretability of latent mixing models.
A novel kernel models latent variable couplings across multiple processes.
problem Modeling latent variable couplings across multiple processes.
method Mutually-dependent Hadamard kernel and latent correlation Gaussian process (LCGP) model.
result The LCGP model recovers latent signal correlations and achieves state-of-the-art performance.
Efficiently samples latent functions in complex data models with sequential structure.
problem Inference of latent functions in probabilistic models with complex data likelihoods.
method Extends Markov chain Monte Carlo techniques to handle sequential structure, enabling efficient sampling of latent variables and parameters.
result Strong performance in growing-data settings, demonstrating scalability.
This paper tackles federated learning for automatic latent variable selection in multi-output Gaussian processes.
problem Challenges in determining the adequate number of latent processes and relying on centralized learning for privacy and computational issues.
method Proposes a hierarchical model with spike-and-slab priors for automatic latent process selection and variational inference-based federated learning algorithm.
result Demonstrates the advantageous features of the proposed federated approach through simulations and real-world data.
Regularizes sparse Gaussian processes for better model performance.
problem Efficient learning of inducing inputs in latent variable models.
method Proposes a regularization approach to balance reconstruction and approximation performance.
result Improves both inference and prediction performance in latent variable models.
Extends Gaussian process regression for non-Gaussian data.
problem Inadequate modeling of uncertainty and over-smoothing in non-Gaussian datasets.
method Time-changed Gaussian processes with Lévy processes.
result Improved modeling of heavy-tailed non-Gaussian behaviors.
Modeling interacting objects with latent Gaussian process ODEs.
problem Time uncertainty-aware modeling of continuous-time dynamics of interacting objects.
method A new model using latent Gaussian process ordinary differential equations to infer independent dynamics and interactions.
result Our model improves long-term predictions and successfully encapsulates independent dynamics and interactions.
GPLVMF improves CARS performance by addressing overfitting and context importance.
problem Overfitting and lack of automatic context importance determination in GP-based CARS.
method GPLVMF applies a non-zero mean function and real-valued latent space to improve GP model performance.
result Significant improvement in performance on real datasets and automatic context importance determination.
GPMM recovers latent signals from noisy mixtures using Bayesian inference.
problem Recovering latent signals from noisy mixed measurements.
method Gaussian process mixture of measurements (GPMM) with Bayesian inference.
result GPMM outperforms standard GP in signal recovery.
A new method for efficient Gaussian process inference using sparse approximations.
problem Scalable and accurate inference for latent Gaussian processes.
method Variational approximation with sparse inverse Cholesky factors and double Kullback-Leibler minimization.
result The proposed method can achieve highly accurate approximations with polylogarithmic time complexity.
Extends multi-output Gaussian processes for heterogeneous outputs.
problem Handling multiple correlated outputs with varying likelihoods.
method Vector-valued Gaussian process prior, linear model of coregionalisation, tractable variational bounds.
result Model performs well on synthetic and real datasets.
Enhances GP regression by learning correlated tasks through latent processes.
problem Improving multi-task learning performance using Gaussian Processes.
method Proposes a new model decomposing covariance matrix into latent processes and parallelizable learning algorithm.
result Significant performance improvements on multiple datasets compared to existing methods.
GPIRT uses Gaussian processes to estimate latent traits and IRFs from binary responses.
problem Nonparametric IRT models struggle to estimate flexible IRFs and latent traits simultaneously.
method GPIRT employs Gaussian process priors to relax IRF assumptions while estimating latent traits.
result GPIRT provides a flexible solution to IRT challenges, including active learning.
Bayesian model captures spatial correlations in data.
problem Modeling spatial correlations in high-dimensional data.
method Structured Bayesian Gaussian process latent variable model with parameterized spatial kernel and structure-exploiting algebra.
result Inference is tractable with computational complexity similar to traditional Bayesian GP-LVM.
Paper uses Gaussian processes to handle shared latent confounders in causal inference.
problem Bias in causal effect estimates due to shared latent confounders.
method Hierarchical Bayesian model, Gaussian processes with structured latent confounders (GP-SLC), Monte Carlo inference algorithm.
result GP-SLC provides accurate estimates of individual treatment effects with minimal assumptions.
Efficiently infers Gaussian process density models with Gibbs sampling and variational methods.
problem Density estimation for complex, nonparametric models.
method Augmented likelihood with latent variables, Gibbs sampling, and variational mean field approximations.
result Efficient inference for Gaussian process density models with up to thousands of data points.
A scalable GPVAE method using local adjacencies to approximate GP inference.
problem Scalability issues in exact GP inference for large-scale GPVAEs.
method Neighbour-driven approximation strategy that confines computations to nearest neighbours.
result Outperforms other GPVAE variants in predictive performance and computational efficiency.
WGPLVM learns submanifolds from wrapped data on Riemannian manifolds.
problem Learning submanifolds from wrapped data on Riemannian manifolds.
method Extends Gaussian process latent variable models to Riemannian manifolds.
result Improves performance on encoding, visualization, and uncertainty quantification tasks.
The Gaussian process latent variable model (GP-LVM) is a popular approach to non-linear probabilistic dimensionality reduction. One design choice for the model is the number of latent variables. We present a spike and slab prior for the GP-LVM and propose an efficient variational inference procedure that gives a lower …
Model captures complex neural dynamics with Gaussian process and RNN.
problem Challenges in extracting latent dynamics from noisy neural data.
method Gaussian process recurrent neural networks (GP-RNN) for nonlinear, non-Markovian dynamics.
result Outperforms state-of-the-art methods in reconstructing latent dynamics.
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.
High dimensional time series are endemic in applications of machine learning such as robotics (sensor data), computational biology (gene expression data), vision (video sequences) and graphics (motion capture data). Practical nonlinear probabilistic approaches to this data are required. In this paper we introduce the v…
Aggregates models from different datasets using shared latent structures.
problem Aggregating models from heterogeneous datasets with shared latent structures.
method Bayesian nonparametrics for identifying correspondences among local model parameterizations.
result Framework successfully aggregates various model types across different applications.
The study addresses negative transfer in multi-output Gaussian processes by proposing latent structures.
problem Negative transfer in multi-output Gaussian processes leading to decreased performance.
method Defining negative transfer, deriving conditions for avoiding it, proposing latent structures.
result Latent structures can avoid negative transfer and scale to large datasets.
Enhances MTGP for better hierarchical latent interactions.
problem Current MTGPs struggle with hierarchical latent interactions.
method Proposes a novel kernel representation for hierarchical interactions in LMC of MTGP.
result Promotes knowledge transferring in MTGP through hierarchical interactions.
Bayesian model learns complex multivariate dependencies.
problem Learning dependency structures across multiple dimensions.
method Flexible Gaussian process priors and Dirichlet process for structure learning.
result Efficient variational inference for model parameters.
Derives a Matern Gaussian process on hypergraphs for regression and embedding.
problem Regression and embedding of vertices in hypergraphs with uncertainty.
method Derives a Matern Gaussian process on hypergraphs, embeds vertices into latent space, identifies inducing vertices for scalable inference.
result Enables estimation of regression models with hypergraph structure informed correlation and uncertainty.
Scalable Gaussian processes with latent Kronecker structure for large datasets.
problem Limited scalability of Gaussian processes for large datasets.
method Leveraging latent Kronecker structure, projecting kernel matrix onto latent Kronecker product, using iterative linear system solvers and pathwise conditioning.
result Outperforms state-of-the-art sparse and variational GPs on real-world datasets with up to five million examples.
Enhances dynamic system modeling with multiplicative latent forces.
problem Handling sparse data and complex models in dynamic systems.
method Extends latent force models to include multiplicative interactions and introduces an approximation method for inference.
result Improved control over trajectory geometry through multiplicative interactions.
Improves Bayesian optimisation for engineering design problems with many variables.
problem Efficiently searching for global minima in high-dimensional design spaces.
method Integrates input and output data to identify a reduced latent subspace using probabilistic partial least squares.
result Significant improvements in convergence to the global minimum compared to existing methods.