2013/08/27 by Isambi Sailon Mbalawata, Mbalawata, Isambi S., Simo Särkkä +5
Computer Science · Mathematics · #Bayesian Methods and Mixture Models #FOS: Mathematics #Gaussian Processes and Bayesian Inference #Markov Chains and Monte Carlo Methods #Statistics Theory (math.ST) #Target Tracking and Data Fusion in Sensor Networks
paper · pdf · doi:10.48550/arxiv.1308.5875
openalex publication_date 2013/08/27 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28
Markov chain Monte Carlo (MCMC) methods are powerful computational tools for\nanalysis of complex statistical problems. However, their computational\nefficiency is highly dependent on the chosen proposal distribution, which is\ngenerally difficult to find. One way to solve this problem is to use adaptive\nMCMC algorithms which automatically tune the statistics of a proposal\ndistribution during the MCMC run. A new adaptive MCMC algorithm, called the\nvariational Bayesian adaptive Metropolis (VBAM) algorithm, is developed. The\nVBAM algorithm updates the proposal covariance matrix using the variational\nBayesian adaptive Kalman filter (VB-AKF). A strong law of large numbers for the\nVBAM algorithm is proven. The empirical convergence results for three simulated\nexamples and for two real data examples are also provided.\n