Article
Statistics & Probability
Andrew J. Holbrook
Summary: We propose a hybrid quantum computing strategy for parallel MCMC algorithms that generate multiple proposals at each step. This strategy uses the Gumbel-max trick to turn the accept-reject step into a discrete optimization problem, enabling quantum parallelization. By combining this strategy with insights from parallel MCMC literature, we can embed target density evaluations within Grover's quantum search algorithm. This combined approach reduces the required number of target evaluations from O(P) to O(vP) .
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2023)
Article
Computer Science, Theory & Methods
Jonas Latz, Juan P. Madrigal-Cianci, Fabio Nobile, Raul Tempone
Summary: In this work, two generalizations of the Parallel Tempering algorithm are introduced, with state-dependent swapping rates inspired by a continuous time Infinite Swapping algorithm. The analysis of reversibility and ergodicity properties show that these generalized PT algorithms significantly improve sampling efficiency compared to more traditional sampling algorithms.
STATISTICS AND COMPUTING
(2021)
Article
Statistics & Probability
Saifuddin Syed, Alexandre Bouchard-Cote, George Deligiannidis, Arnaud Doucet
Summary: Parallel tempering (PT) methods are widely used for sampling complex high-dimensional probability distributions by relying on a set of interacting auxiliary chains to improve exploration of the state space. The comparison between reversible and non-reversible PT schemes reveals the dominance of the latter in both theoretical and empirical aspects, leading to the identification of optimal annealing schedules and iterative schemes for non-reversible PT. The proposed methodology is applicable to various scenarios where sampling from a distribution with respect to a reference distribution and computing the normalizing constant are required.
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
(2022)
Article
Mathematics, Applied
Riccardo Tosi, Ramon Amela, Rosa M. Badia, Riccardo Rossi
Summary: The necessity of dealing with uncertainties is increasing in various fields of science and engineering. The proposed asynchronous framework for Monte Carlo and Multilevel Monte Carlo methods aims to improve computational efficiency by introducing a new level of parallelism between batches. This approach maintains the reliability of state-of-the-art techniques while enhancing computational efficiency.
JOURNAL OF SCIENTIFIC COMPUTING
(2021)
Article
Computer Science, Software Engineering
Jouni Helske
Summary: The R package walker extends Bayesian general linear models to handle time-varying effects of explanatory variables. This approach enables the modeling of intervention effects that gradually increase over time, such as changes in tax policy. The algorithm utilizes Hamiltonian Monte Carlo provided by Stan software to marginalize over the regression coefficients in a state space representation of the model, allowing for efficient low-dimensional sampling.
Article
Construction & Building Technology
Genshen Fang, Miaomiao Wei, Lin Zhao, Kun Xu, Shuyang Cao, Yaojun Ge
Summary: A stochastic simulation-based algorithm is developed to determine the design extreme wind speed vertical profile of tropical cyclones, providing a rational estimation of TC-induced wind loadings for high-rise structures.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Moises Cordeiro-Costas, Daniel Villanueva, Andres E. Feijoo-Lorenzo, Javier Martinez-Torres
Summary: A method is proposed in this paper to synthetically generate sequences of wind speed values satisfying statistical distributions and imposing spatial and temporal correlations. The method was successfully checked under different scenarios, with high accuracy in the results.
APPLIED SCIENCES-BASEL
(2021)
Article
Mathematics, Applied
Benedict Leimkuhler, Matthias Sachs
Summary: This article studies numerical methods for solving the generalized Langevin equation (GLE), and proposes an integration method that outperforms other schemes in terms of sampling accuracy and robustness. The obtained GLE-based sampling scheme can also be more efficient than state-of-the-art sampling schemes based on underdamped Langevin dynamics in some cases.
SIAM JOURNAL ON SCIENTIFIC COMPUTING
(2022)
Article
Computer Science, Theory & Methods
Alix Marie d'Avigneau, Sumeetpal S. Singh, Lawrence M. Murray
Summary: Efficient MCMC algorithms are crucial in Bayesian inference, especially in the context of parallel tempering. This study addresses the issue of randomly varying local move completion times in multi-processor parallel tempering by imposing real-time deadlines on the parallel local moves and performing exchanges at these deadlines without any processor idling. The methodology of exchanges at real-time deadlines is shown to lead to significant performance enhancements without introducing bias, with potential applications in ABC algorithms for parameter estimation.
STATISTICS AND COMPUTING
(2021)
Article
Engineering, Civil
C. Pelaez-Rodriguez, J. Perez-Aracil, L. Prieto-Godino, S. Ghimire, R. C. Deo, S. Salcedo-Sanz
Summary: A novel fuzzy-based cascade ensemble of regression models is proposed to accurately estimate extreme wind speed values. It involves partitioning the training data into fuzzy-soft clusters based on the target variable value, and training a specific regression model within each cluster. The predictions made by individual models are then integrated into a fuzzy-based ensemble using a pertinence value assigned to each model. The performance of the proposed methodology has been evaluated using real data from wind farms in Spain.
JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS
(2023)
Article
Computer Science, Theory & Methods
Minas Karamanis, Florian Beutler
Summary: Slice sampling is a powerful Markov Chain Monte Carlo algorithm, but sensitive to user-specified parameters and struggles with strongly correlated distributions. Ensemble Slice Sampling introduces a new class of algorithms that adaptively tune parameters and utilize parallel walkers to efficiently handle strong correlations, significantly improving sampling efficiency.
STATISTICS AND COMPUTING
(2021)
Article
Energy & Fuels
Olga Poddaeva, Anastasia Fedosova
Summary: The paper investigates the impact of extreme wind speeds on building design and presents a statistical analysis method to test the correlation between different wind speeds and directions. Two case studies in different regions of Russia are examined to provide recommendations for the building stage.
Article
Computer Science, Theory & Methods
Wendy K. Tam Cho, Yan Y. Liu
Summary: The algorithm developed combines the advantages of evolutionary algorithms and Markov Chain Monte Carlo algorithms to sample spatial partitions within a large, complex, and constrained spatial state space. It uses a Multiple-Try Metropolis Markov Chain model to adaptively update the Markov chain based on local optimality information identified through directed search. The reach of the algorithm is further expanded by harnessing the computational power of massively parallel computing architecture through the integration of a parallel EA framework.
STATISTICS AND COMPUTING
(2021)
Article
Engineering, Mechanical
P. L. Green, L. J. Devlin, R. E. Moore, R. J. Jackson, J. Li, S. Maskell
Summary: This paper discusses the optimization of the 'L-kernel' in Sequential Monte Carlo samplers to improve performance, resulting in reduced variance of estimates and fewer resampling requirements.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Computer Science, Interdisciplinary Applications
DanHua ShangGuan
Summary: The Monte Carlo method is a powerful tool in many research fields, but the increasing complexity of physical models and mathematical models requires efficient algorithms to overcome the computational cost.
JOURNAL OF COMPUTATIONAL PHYSICS
(2021)
Article
Statistics & Probability
S. Reza H. Shojaei, Yadollah Waghei, Mohsen Mohammadzadeh
JOURNAL OF APPLIED STATISTICS
(2018)
Article
Statistics & Probability
Behzad Mahmoudian
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2017)
Article
Statistics & Probability
K. Motarjem, M. Mohammadzadeh, A. Abyar
STATISTICAL PAPERS
(2020)
Article
Engineering, Environmental
Ramin Khavarzadeh, Mohsen Mohammadzadeh, Jorge Mateu
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2018)
Article
Statistics & Probability
Behzad Mahmoudian
STATISTICS & PROBABILITY LETTERS
(2018)
Article
Statistics & Probability
Zohreh Fallah Mohsenkhani, Mohsen Mohhamadzadeh, Taban Baghfalaki
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
(2019)
Article
Statistics & Probability
C. Ayyad, J. Mateu, M. Omidi, I. Tamayo-Uria, M. Mohammadzadeh
STATISTICA NEERLANDICA
(2019)
Article
Statistics & Probability
Samira Zahmatkesh, Mohsen Mohammadzadeh
Summary: This paper discusses methods for considering missing values in spatial data and proposes a joint spatial Bayesian shared parameter model. By modeling the missing process and measurement process together, using Bayesian inference for analysis, and conducting a simulation study on lake surface water temperature data, the efficiency of the spatial joint model is confirmed.
STATISTICAL PAPERS
(2021)
Article
Statistics & Probability
Mohadeseh Alsadat Farzammehr, Mohsen Mohammadzadeh, Mohammad Reza Zadkarami, Geoffrey J. McLachlan
Summary: This research relaxes the normality assumption of a generalized linear mixed model by using an unrestricted multivariate skew-normal distribution. Parameter estimation is done through a Bayesian inference algorithm, and the proposed skew normal spatial mixed model is compared with the normal spatial mixed model through simulation studies and analysis of real data.
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
(2022)
Article
Mathematics, Applied
Elaheh Lotfian, Mohsen Mohammadzadeh
Summary: In this study, a new hybrid algorithm is developed to solve the bi-objective optimization problems of soil sampling, and it is compared with four other multi-objective optimization algorithms. The results show that the proposed hybrid algorithm outperforms other algorithms in terms of diversity and dominance solutions.
COMPUTATIONAL & APPLIED MATHEMATICS
(2023)
Article
Engineering, Electrical & Electronic
Sajedeh Lashgari, Mohsen Mohammadzadeh, Foad Ghaderi
Summary: In this article, a plan based on Adaptive Elastic-net Sliced Inverse Regression was proposed to identify risk factors for Covid-19 disease in the presence of collinearity between explanatory variables. The proposed method demonstrated a more stable and accurate model for variable selection by incorporating the penalty of elastic-net and sliced inverse regression to achieve dimension reduction. The experimental results showed significant reductions in standard error compared to previous superior methods, indicating the effectiveness of the proposed method for analyzing Covid-19 data.
IET SIGNAL PROCESSING
(2023)
Article
Statistics & Probability
Mohammad Mehdi Saber, Alireza Nematollahi, Mohsen Mohammadzadeh
Summary: The study discusses the limitations of earlier approaches to spatial prediction issues, which assume Gaussian random field for data that do not follow this distribution. It proposes the use of generalized skew Laplace distributions as an alternative method to define skew and heavy tailed random fields for Bayesian prediction. The performance of this model is evaluated through simulation studies and a real-world problem.
JOURNAL OF STATISTICAL THEORY AND APPLICATIONS
(2021)
Article
Geosciences, Multidisciplinary
Mehdi Boroumandi, Mashalah Khamehchiyan, Mohammad Reza Nikoudel, Mohsen Mohammadzadeh
Article
Statistics & Probability
Mehdi Omidi, Mohsen Mohammadzadeh
JIRSS-JOURNAL OF THE IRANIAN STATISTICAL SOCIETY
(2018)
Article
Mathematics, Interdisciplinary Applications
Hamid Zareifard, Majid Jafari Khaledi, Firoozeh Rivaz, Mohammad Q. Vahidi-Asl