MCMC Methods for Functions: Modifying Old Algorithms to Make Them Faster
نویسندگان
چکیده
منابع مشابه
MCMC Methods for Functions: Modifying Old Algorithms to Make Them Faster
Markov Chain Monte Carlo methods on function spaces are useful, for example to solve inverse problems. Classical methods su er from poor performance on function space, which makes modi cations of them necessary. This essay provides an overview of certain dimension-independent methods. Discussed are applications, examples, theoretical underpinnings, and the mathematical properties behind these m...
متن کاملMCMC Methods for Functions: Modifying Old Algorithms to Make Them Faster
Many problems arising in applications result in the need to probe a probability distribution for functions. Examples include Bayesian nonparametric statistics and conditioned diffusion processes. Standard MCMC algorithms typically become arbitrarily slow under the mesh refinement dictated by nonparametric description of the unknown function. We describe an approach to modifying a whole range of...
متن کاملUtilize Old Coordinates: Faster Doubly Stochastic Gradients for Kernel Methods
To address the scalability issue of kernel methods, random features are commonly used for kernel approximation (Rahimi and Recht, 2007). They map the input data to a randomized lowdimensional feature space and apply fast linear learning algorithms on it. However, to achieve high precision results, one might still need a large number of random features, which is infeasible in large-scale applica...
متن کاملExtending Annotations to Make them Truly Valuable
Although the basic idea of annotations is rather old most web material does not allow for annotations. Even if it does, annotations are usually little used. However, research shows that annotations are potentially an important part of digital libraries and particularly eLearning: they can help users to learn more easily by (collaboratively) adding comments, links and bookmarks, thus personalizi...
متن کاملMCMC algorithms for Subset Simulation
Subset Simulation is an adaptive simulation method that efficiently solves structural reliability problems with many random variables. The method requires sampling from conditional distributions, which is achieved through Markov Chain Monte Carlo (MCMC) algorithms. This paper discusses different MCMC algorithms proposed for Subset Simulation and introduces a novel approach for MCMC sampling in ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Statistical Science
سال: 2013
ISSN: 0883-4237
DOI: 10.1214/13-sts421