Statistical Analysis of Non-Lattice Data

By Julian Besag. 1975

How researchers see this paper

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

In Statistics and Probability

Citations in the corpus

Neural Autoregressive Distribution Estimation (2016, background): “Other proposals include pseudo-likelihood (Besag, 1975; Marlin et al., 2010), score matching (Hyv¨arinen, 2005; Hyv¨arinen, 2007a,b), noise contrastive estimation (Gutmann and Hyv¨arinen, 2010) and probability ﬂow minimization (Sohl-Dickstein et al., 2011).”
Energy-Inspired Models: Learning with Sampler-Induced Distributions (2019, methodology): “R � To ﬁt the model, many approximate methods have been developed ( e.g. , pseudo log-likelihood [6], contrastive divergence [29, 65], score matching estimator [30], minimum probability ﬂow [64], noise contrastive estimation [27]) to bypass the calculation of the partition function.”
Deep Unsupervised Learning using Nonequilibrium Thermodynamics (2015, background): “Non-parametric methods [8] can also be very effective 1 .”
Representation Learning: A Review and New Perspectives (2012, background): “In particular, these include pseudo-likelihood (Besag, 1975) and ratiomatching (Hyvärinen, 2007).”
Masked Language Model Scoring (2019, methodology): “However, BERT’s MLM objective can be viewed as stochastic maximum pseudolikelihood estimation (MPLE) (Wang and Cho, 2019; Besag, 1975) In this way, MLMs learn an underlying joint distribution whose conditional distributions w t | W \ t are modeled by masking at position t .”
Minimum Probability Flow Learning (2009, background): “…and Carreira-Perpiñán (Welling & Hinton, 2002; CarreiraPerpiñán & Hinton, 2004), Hyvärinen’s score matching (SM) (Hyvärinen, 2005), Besag’s pseudolikelihood (PL) (Besag, 1975), and the minimum velocity learning framework proposed by Movellan (Movellan, 2008a;b; Movellan & McClelland, 1993).”
Recovering intrinsic images from a single image (2005, neutral): “probability of eachMRF [3].”
3D RNA and Functional Interactions from Evolutionary Couplings. (2015, unknown): “Instead of maximizing the likelihood, we instead maximize a surrogate function, the pseudolikelihood (Besag, 1975) which approximates the full likelihood for each sequence 𝝈 = 𝜎!,… ,𝜎! by a product of conditional likelihoods for each site i: 𝑃 𝜎!,… ,𝜎!”
Joint and Conditional Estimation of Tagging and Parsing Models (2001, methodology): “This research was supported by NSF awards 9720368 and 9721276 and NIH award R01 MH60922-01A2. the conditional likelihood or “pseudo-likelihood” of the training data (Besag, 1975).”
Classification in Networked Data: A Toolkit and a Univariate Case Study (2007, unknown): “treat the induced network as a Gaussian field (Besag, 1975) (a random field with soft node labels) constrained such that the labeled nodes maintain their values.”
Markov chain Monte Carlo for a Spatial-Temporal Autologistic Regression Model (2008, background): “Besag (1975) proposed instead to maximize a pseudo-likelihood function, which is the product of the full conditional distributions (1.1).”
Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives (2012, unknown): “In particular, these include pseudo-likelihood (Besag, 1975) and ratio-matching (Hyv ¨ arinen, 2007).”
Learning Graphical Model Parameters with Approximate Marginal Inference (2013, background): “Besag [29] showed that, under certain conditions, this will converge to the true parameter vector as the amount of data becomes infinite.”
Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes (2020, background): “This expression resembles the pseudolikelihood (Besag, 1975), but instead of a single conditional event per output site, the expression in (8) considers all pairs of sites.”
An introduction to exponential random graph (p*) models for social networks (2007, methodology): “Besag (1975) , and was suggested for Markov random graph models by Strauss and Ikeda (1990).”