Gaussian sampling by local perturbations

86 citations recorded by the source corpus.

How researchers see this paper

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

A* Sampling (2014, methodology): “Some are specialized to specific distributions [5], but exact generic methods are based either on (adaptive) rejection sampling [6, 7, 8] or Markov Chain Monte Carlo (MCMC) methods where convergence to the stationary distribution can be guaranteed [9, 10, 11].”
On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations (2013, background): “Recently, [16, 9, 17, 21, 6] explore the different aspects of random MAP predictions with low dimensional perturbation.”
Gaussian Kullback-Leibler approximate inference (2013, methodology): “Marginal variances are approximated either by constructing low rank factorisations of A using iterative Lanczos methods or by perturb and MAP sampling methods (Papandreou and Yuille, 2010; Seeger, 2010; Ko and Seeger, 2012).”
Perturb-and-MAP random fields: Using discrete optimization to learn and sample from energy models (2011, methodology): “While Perturb and-MAP random fields can also be built on energies de fined over continuous labels [20], our focus in this paper will be on random fields over discrete labels.”
On the Partition Function and Random Maximum A-Posteriori Perturbations (2012, methodology): “Other surrogate probability models using computational structures appears in (Papandreou & Yuille, 2010; Kulesza & Taskar, 2010).”