Optimized Population Monte Carlo
نویسندگان
چکیده
Adaptive importance sampling (AIS) methods are increasingly used for the approximation of distributions and related intractable integrals in context Bayesian inference. Population Monte Carlo (PMC) algorithms a subclass AIS methods, widely due to their ease adaptation. In this paper, we propose novel algorithm that exploits benefits PMC framework includes more efficient adaptive mechanisms, exploiting geometric information target distribution. particular, adapts location scale parameters set densities (proposals). At each iteration, adapted by combining versatile resampling strategy (i.e., using previous weighted samples) with an advanced optimization-based scheme. Local second-order distribution is incorporated through preconditioning matrix acting as scaling metric onto gradient direction. A damped Newton approach adopted ensure robustness The resulting also update proposals. We discuss several key theoretical foundations proposed approach. Finally, show successful performance method three numerical examples, involving challenging distributions.
منابع مشابه
Optimized Monte Carlo Methods
I discuss optimized data analysis and Monte Carlo methods. Reweighting methods are discussed through examples, like Lee-Yang zeroes in the Ising model and the absence of deconfinement in QCD. I discuss reweighted data analysis and multi-hystogramming. I introduce Simulated Tempering, and as an example its application to the Random Field Ising Model. I illustrate Parallel Tempering, and discuss ...
متن کاملPopulation Monte Carlo algorithms
We give a cross-disciplinary survey on “population” Monte Carlo algorithms. In these algorithms, a set of “walkers” or “particles” is used as a representation of a high-dimensional vector. The computation is carried out by a random walk and split/deletion of these objects. The algorithms are developed in various fields in physics and statistical sciences and called by lots of different terms – ...
متن کاملFeedback-optimized parallel tempering Monte Carlo
We introduce an algorithm for systematically improving the efficiency of parallel tempering Monte Carlo simulations by optimizing the simulated temperature set. Our approach is closely related to a recently introduced adaptive algorithm that optimizes the simulated statistical ensemble in generalized broad-histogram Monte Carlo simulations. Conventionally, a temperature set is chosen in such a ...
متن کاملOptimized Monte Carlo Method for glasses
A new Monte Carlo algorithm is introduced for the simulation of supercooled liquids and glass formers, and tested in two model glasses. The algorithm is shown to thermalize well below the Mode Coupling temperature and to outperform other optimized Monte Carlo methods. Using the algorithm, we obtain finite size effects in the specific heat. This effect points to the existence of a large correlat...
متن کاملPopulation Monte Carlo Path Tracing
We present a novel global illumination algorithm which distributes more image samples on regions with perceptually high variance. Our algorithm iterates on a population of pixel positions used to estimate the intensity of each pixel in the image. A member kernel function, which automatically adapts to approximate the target ditribution by using the information collected in previous iterations, ...
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: IEEE Transactions on Signal Processing
سال: 2022
ISSN: ['1053-587X', '1941-0476']
DOI: https://doi.org/10.1109/tsp.2022.3172619