论文信息 - Challenges and Advances in High Dimensional and High Complexity Monte Carlo Computation and Theory

Challenges and Advances in High Dimensional and High Complexity Monte Carlo Computation and Theory

It is commonly recognized in the literature that the only possible way to estimate many realistic highly structured and high dimensional statistical models that properly describe the real world and the complex interactions among the variables that come into play, is by using computational tools such as Monte Carlo methods. The development and application of Monte Carlo methods has been an active research area for the last two decades. Many useful Monte Carlo techniques have been proposed in the literature, including Markov chain Monte Carlo (MCMC), sequential Monte Carlo, adaptive MCMC, perfect sampling, and quantum Monte Carlo.

[1] M. Caffarel,et al. Zero-Variance Principle for Monte Carlo Algorithms , 1999, cond-mat/9911396.

[2] Massimiliano Bonomi,et al. Metadynamics , 2019, ioChem-BD Computational Chemistry Datasets.

[3] J. Propp,et al. Exact sampling with coupled Markov chains and applications to statistical mechanics , 1996 .

[4] A. Gelman,et al. Weak convergence and optimal scaling of random walk Metropolis algorithms , 1997 .

[5] S. Russo,et al. Zero-variance zero-bias quantum Monte Carlo estimators for the electron density at a nucleus. , 2011, The Journal of chemical physics.

[6] Michele Parrinello,et al. Exploring the free energy surfaces of clusters using reconnaissance metadynamics. , 2011, The Journal of chemical physics.