Slice Sampling

By Radford M. Neal. Annals of Statistics, 2003

985 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/2099b15fe75c2e6addcb9a500214b490725b7d51

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Asymptotically exact inference in differentiable generative models (2016, background): “latent marginal p Z [z] and output conditional p Y jZ [yjz] are of known forms (e.g. Gaussian). However such hierarchical model structures are known to be challenging for MCMC methods to explore well [28], with often large variations in scale across the joint space and tight coupling between latent ”
Spatial Modeling With Spatially Varying Coefficient Processes (2003, methodology): “Bayesian models using the marginal likelihoodsin either (4), (9), or (11) are easily tted using a slice Gibbs sampler as discussed by Agarwal and Gelfand (2001) (see Neal 2002, as well).”
Stick-breaking Construction for the Indian Buffet Process (2007, methodology): “Slice sampling is an auxiliary variable method that samples from a distribution by sampling uniformly from the region under its density function [12].”
Efficient Gradient-Based Inference through Transformations between Bayes Nets and Neural Nets (2014, methodology): “aving between centered and non-centered parameterizations, as was shown in (Yu & Meng, 2011). Auxiliary variables are used for data augmentation (see (Van Dyk & Meng, 2001) or slice sampling (Neal, 2003)) where, in contrast with our method, sampling is performed in a higher-dimensional augme”
Efficient sampling methods for truncated multivariate normal and student-t distributions subject to linear inequality constraints (2015, methodology): “The slice sampler (Neal (2003)) is also an appropriate technique for the sampling problem of the TMVN distributions.”
Statistical Rejection Sampling Improves Preference Optimization (2023, methodology): “Statistical rejection sampling (Neal, 2003) is a statistical approach used to generate samples from a target distribution using a proposal distribution.”
Nonstationary multivariate process modeling through spatially varying coregionalization (2004, methodology): “) Another possibility is the moving average approach of Ver Hoef and Barry (1998). The technique is also called kernel convolution and is a wellknown approach for creating rich classes of stationary spatial processes.”
Slice sampling covariance hyperparameters of latent Gaussian models (2010, background): “Stepping-out procedures [2] could be used to adapt initial scales that are too small.”
A Tutorial on Bayesian Optimization (2018, methodology): “…distribution on f ( x ) marginalizing over all possible values of the hyperparameters, This integral is typically intractable, but we can approximate it through sampling: where (ˆ η j : j = 1 , . . . , J ) are sampled from P ( η | f ( x 1: n )) via an MCMC method, e.g., slice sampling (Neal, 2003).”
brms: An R Package for Bayesian Multilevel Models Using Stan (2017, methodology): “…are primarily using combinations of Metropolis-Hastings updates (Metropolis, Rosenbluth, Rosenbluth, Teller, and Teller 1953; Hastings 1970) and Gibbs-sampling (Geman and Ge-man 1984; Gelfand and Smith 1990), sometimes also coupled with slice-sampling (Damien, WakeĄeld, and Walker 1999; Neal 2003).”
An Introduction to MCMC for Machine Learning (2004, background): “Algorithmic improvements and convergence results are presented in Mira (1999) and Neal (2000).”