Model-averaged ℓ1regularization using Markov chain Monte Carlo model composition
نویسندگان
چکیده
منابع مشابه
Model - Averaged ` 1 Regularization using Markov Chain Monte Carlo Model Composition
This paper studies combining `1 regularization and Markov chain Monte Carlo model composition techniques for Bayesian model averaging (BMA). The main idea is to resolve the model uncertainty issues arising from path point selection by treating the `1 regularization path as a model space for BMA. The method is developed for linear and logistic regression, and applied to sample classification in ...
متن کاملMarkov chain Monte Carlo over Model Structures
Introduction MCMCMS implements a generic framework for constructing Markov chains. It can be used to perform statistical machine learning in a Bayesian framework. It presents a modular, high level approach to performing MCMC simulations over statistical models that can explain observed data [1]. The two main benefits of MCMCMS are its prior-centric construction of the chain, that does away with...
متن کاملEnsemble Bayesian model averaging using Markov Chain Monte Carlo sampling
Bayesian model averaging (BMA) has recently been proposed as a statistical method to calibrate forecast ensembles from numerical weather models. Successful implementation of BMA however, requires accurate estimates of the weights and variances of the individual competing models in the ensemble. In their seminal paper (Raftery et al. Mon Weather Rev 133:1155–1174, 2005) has recommended the Expec...
متن کاملMarkov Chain Monte Carlo
Markov chain Monte Carlo is an umbrella term for algorithms that use Markov chains to sample from a given probability distribution. This paper is a brief examination of Markov chain Monte Carlo and its usage. We begin by discussing Markov chains and the ergodicity, convergence, and reversibility thereof before proceeding to a short overview of Markov chain Monte Carlo and the use of mixing time...
متن کاملMarkov Chain Monte Carlo
This paper gives a brief introduction to Markov Chain Monte Carlo methods, which offer a general framework for calculating difficult integrals. We start with the basic theory of Markov chains and build up to a theorem that characterizes convergent chains. We then discuss the MetropolisHastings algorithm.
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: Journal of Statistical Computation and Simulation
سال: 2013
ISSN: 0094-9655,1563-5163
DOI: 10.1080/00949655.2013.861839