Probabilistic Graphical Models

By Sargur N. Srihari, L. V. D. Gaag, Ad Feelders. 2014

609 citations recorded by the source corpus.

Subfields: Building and Construction, Computer Networks and Communications, Probabilistic & Bayesian Methods, Signal Processing

How researchers see this paper

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

In Building and Construction

In Computer Networks and Communications

In Probabilistic & Bayesian Methods

In Signal Processing

Citations in the corpus

Adaptive Stochastic Dual Coordinate Ascent for Conditional Random Fields (2017, methodology): “The conditional random field (CRF) model (Lafferty et al., 2001) is a common tool in natural language processing and computer vision for structured prediction. The optimization of this model is notoriously challenging. Schmidt et al. (2015) describes a practical implementation of the stochastic aver”
HoloClean: Holistic Data Repairs with Probabilistic Inference (2017, positive): “HoloClean relies on factor graphs [27] to represent the probability distribution over variables T c .”
Score-based causal learning in additive noise models (2013, methodology): “Score-based methods are widely used for fitting Gaussian SEMs [14] or discrete Bayesian networks.[15] Maximum a posteriori estimation was used in the setting of nonlinear models with Gaussian noise by Imoto et al.”
The Emergence of Organizing Structure in Conceptual Representation (2016, background): “3) is a special case of learning the structure of an undirected graphical model, a generally intractable problem that requires heuristic algorithms not guaranteed to reach the global optimum (Koller & Friedman, 2009).”
Unsupervised Generative Modeling Using Matrix Product States (2017, background): “It is known that when graphical models have an appropriate structure (such as a chain or a tree), the inference can be done efficiently [46,47], while these structural constraints also limit the application of graphical models with intractable partition functions.”
Partition MCMC for Inference on Acyclic Digraphs (2015, background): “From theMarkov assumption (Koller and Friedman 2009) that each variable Xi is independent of its nondescendants given its parents in the graph G, it follows that the joint probability distribution described by the Bayesian network B factorizes as P(X1, . . . ,Xn) = n∏ i P(Xi|Pai) .”
Multilabel Image Classification With Regional Latent Semantic Dependencies (2016, methodology): “The probabilistic graphical models [9] are usually employed in previous works [29], [30], [10], [11], [31] to model the image feature-label joint distribution.”
A Non-parametric Bayesian Network Prior of Human Pose (2013, neutral): “Kullback-Leibler divergence to q(X), [13],”
On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations (2013, neutral): “To learn more about its roles in machine learning, as well as its standard samplers, we refer the interested reader to the textbook [11].”
Efficient Sampling and Structure Learning of Bayesian Networks (2018, background): “The distribution a Bayesian network represents is assumed to satisfy the Markov property (described for example in Koller and Friedman, 2009) that each variable X i is independent of its non-descendants given its parents Pa i , allowing the joint probability distribution to factorise as Learning…”
Structure Learning in Graphical Modeling (2016, neutral): “Textbooks on this problem include Spirtes et al. (2000), Neapolitan (2004), and Koller & Friedman (2009).”
Information-theoretic evaluation of predicted ontological annotations (2013, neutral): “According to this assumption, each term is independent of its ancestors, given its parents and, thus, the full joint probability can be factorized as a product of individual terms obtained from the set of conditional probability tables associated with each term (Koller and Friedman, 2009).”
Detecting crosstalk errors in quantum information processors (2019, methodology): “Specifically, we show how to adapt techniques developed to learn causal structure in Bayesian networks [41, 27], to detect the”
The OS* Algorithm: a Joint Approach to Exact Optimization and Sampling (2012, methodology): “7 To improve this upper bound, we use the conditioning idea (see e.g. [Koller and Friedman, 2009], chap.”
Guidelines for a graph-theoretic implementation of structural equation modeling (2012, neutral): “In the absence of a covariance matrix approach, linkages/edges E in the graph G must be judged individually, which requires the use of graphical modeling methods (e.g., Koller and Friedman 2009).”