Elliptical slice sampling

Abstract

Many probabilistic models introduce strong dependencies between variables using a latent multivariate Gaussian distribution or a Gaussian process. We present a new Markov chain Monte Carlo algorithm for performing inference in models with multivariate Gaussian priors. Its key properties are: 1) it has simple, generic code applicable to many models, 2) it has no free parameters, 3) it works well for a variety of Gaussian process based models. These properties make our method ideal for use while model building, removing the need to spend time deriving and tuning updates for more complex algorithms.

8 pages, 6 figures, appearing in AISTATS 2010 (JMLR: W&CP volume 6). Differences from first submission: some minor edits in response to feedback.

Cited by in corpus (104)

• Bayesian Optimization with Unknown Constraints
• Estimation of COVID-19 spread curves integrating global data and borrowing information
• Slice sampling covariance hyperparameters of latent Gaussian models
• Variational Fourier features for Gaussian processes
• Bayesian Distributed Lag Interaction Models to Identify Perinatal Windows of Vulnerability in Children's Health
• Discovering Latent Network Structure in Point Process Data
• Lognormal and Gamma Mixed Negative Binomial Regression
• Piecewise-Deterministic Markov Chain Monte Carlo
• Dependent Multinomial Models Made Easy: Stick Breaking with the Pólya-Gamma Augmentation
• MCMC for Variationally Sparse Gaussian Processes
• Bayesian leave-one-out cross-validation approximations for Gaussian latent variable models
• Incorporating Side Information in Probabilistic Matrix Factorization with Gaussian Processes
• An Efficient Bayesian Inference Framework for Coalescent-Based Nonparametric Phylodynamics
• Gaussian Probabilities and Expectation Propagation
• Gaussian Process Regression with Heteroscedastic or Non-Gaussian Residuals
• Kernel Machine and Distributed Lag Models for Assessing Windows of Susceptibility to Environmental Mixtures in Children's Health Studies
• Nonparametric Bayesian Topic Modelling with the Hierarchical Pitman-Yor Processes
• Bayesian Modeling with Gaussian Processes using the GPstuff Toolbox
• Unbiased Markov chain Monte Carlo with couplings
• High-Dimensional Bayesian Regularised Regression with the BayesReg Package
• Gaussian Processes for Survival Analysis
• Kernel Topic Models
• Exact Gaussian Processes on a Million Data Points
• State-Space Inference for Non-Linear Latent Force Models with Application to Satellite Orbit Prediction
• Estimating effective population size changes from preferentially sampled genetic sequences
• Scalable Nonparametric Bayesian Inference on Point Processes with Gaussian Processes
• Pseudo-Marginal Slice Sampling
• Generalised Wishart Processes
• Preconditioning Kernel Matrices
• Properties of the Affine Invariant Ensemble Sampler in high dimensions
• Subspace Inference for Bayesian Deep Learning
• Estimating redshift distributions using Hierarchical Logistic Gaussian processes
• Tuning Fairness by Balancing Target Labels
• Scalable Exact Inference in Multi-Output Gaussian Processes
• Bayesian Structured Sparsity from Gaussian Fields
• Efficient Bayesian Nonparametric Modelling of Structured Point Processes
• Bayesian Inference for Generalized Linear Model with Linear Inequality Constraints
• Sequential Gaussian Processes for Online Learning of Nonstationary Functions
• Cold Posteriors and Aleatoric Uncertainty
• Integrals over Gaussians under Linear Domain Constraints
• Bayesian Structured Prediction Using Gaussian Processes
• Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
• Nonparametric Bayesian Density Modeling with Gaussian Processes
• Bayesian Model Selection of Lithium-Ion Battery Models via Bayesian Quadrature
• Data Augmentation for Bayesian Deep Learning
• The Ridgelet Prior: A Covariance Function Approach to Prior Specification for Bayesian Neural Networks
• Physiological Gaussian Process Priors for the Hemodynamics in fMRI Analysis
• Uncertainty Estimates for Ordinal Embeddings
• Geometric convergence of elliptical slice sampling
• Bayesian inference for dynamic vine copulas in higher dimensions
• URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks
• A linear noise approximation for stochastic epidemic models fit to partially observed incidence counts
• Trust-Region Variational Inference with Gaussian Mixture Models
• Efficient Bayesian Inference of Sigmoidal Gaussian Cox Processes
• A Probabilistic State Space Model for Joint Inference from Differential Equations and Data
• Exploring the Uncertainty Properties of Neural Networks' Implicit Priors in the Infinite-Width Limit
• Stein Variational Gaussian Processes
• Horseshoe-based Bayesian nonparametric estimation of effective population size trajectories
• Flexible Bayesian Dynamic Modeling of Correlation and Covariance Matrices
• Transitional annealed adaptive slice sampling for Gaussian process hyper-parameter estimation
• Gaussian Process-Based Bayesian Nonparametric Inference of Population Trajectories from Gene Genealogies
• A Probabilistic Perspective on Gaussian Filtering and Smoothing
• Computer emulation with non-stationary Gaussian processes
• A Common Derivation for Markov Chain Monte Carlo Algorithms with Tractable and Intractable Targets
• Gaussian Process Single Index Models for Conditional Copulas
• Flexible sampling of discrete data correlations without the marginal distributions
• GPIRT: A Gaussian Process Model for Item Response Theory
• Learning Temporal Evolution of Spatial Dependence with Generalized Spatiotemporal Gaussian Process Models
• A dependent partition-valued process for multitask clustering and time evolving network modelling
• A New Monte Carlo Based Algorithm for the Gaussian Process Classification Problem
• Space and circular time log Gaussian Cox processes with application to crime event data
• Analyzing Car Thefts and Recoveries with Connections to Modeling Origin-Destination Point Patterns
• phylodyn: an R package for phylodynamic simulation and inference
• Pseudo-marginal Bayesian inference for supervised Gaussian process latent variable models
• Marginalising over Stationary Kernels with Bayesian Quadrature
• Sequential sampling of Gaussian process latent variable models
• Accelerated Parallel Non-conjugate Sampling for Bayesian Non-parametric Models
• A monotone single index model for spatially referenced multistate current status data
• A Probabilistic Approach to Nonparametric Local Volatility
• Bayesian Inference for Gaussian Process Classifiers with Annealing and Pseudo-Marginal MCMC
• Pseudo-Marginal Bayesian Inference for Gaussian Processes
• Parallel MCMC with Generalized Elliptical Slice Sampling
• Approximate Marginal Posterior for Log Gaussian Cox Processes
• Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties
• Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate
• A Tucker decomposition process for probabilistic modeling of diffusion magnetic resonance imaging
• Multi-level hypothesis testing for populations of heterogeneous networks
• Spatial Process Gradients and Their Use in Sensitivity Analysis for Environmental Processes
• Accelerating Metropolis-Hastings with Lightweight Inference Compilation
• The Soft Multivariate Truncated Normal Distribution with Applications to Bayesian Constrained Estimation
• Learning Causally-Generated Stationary Time Series
• Modeling Random Directions in 2D Simplex Data
• Bayesian Inference in High-Dimensional Time-Serieswith the Orthogonal Stochastic Linear Mixing Model
• Gaussian Processes on Hypergraphs
• Choice functions based multi-objective Bayesian optimisation
• Bayesian Nonparameteric Multiresolution Estimation for the American Community Survey
• String and Membrane Gaussian Processes
• High-resolution Probabilistic Precipitation Prediction for use in Climate Simulations
• On MCMC for variationally sparse Gaussian processes: A pseudo-marginal approach
• Fast matrix computations for functional additive models
• Generalized Elliptical Slice Sampling with Regional Pseudo-priors
• A Latent Slice Sampling Algorithm
• Long-term Spatial Modeling for Characteristics of Extreme Heat Events
• Good Classifiers are Abundant in the Interpolating Regime