APES:近似后验集成采样器
APES: Approximate Posterior Ensemble Sampler
AI总结:
本文提出APES算法,利用核密度估计和径向基插值构建自适应提议分布,解决MCMC在高维复杂分布中采样收敛慢的问题,并在Rosenbrock函数上自相关时间比仿射不变集成采样器小140倍。
摘要:
本文提出了一种新方法,用于从难以使用马尔可夫链蒙特卡洛(MCMC)方法采样的目标分布中生成样本。传统MCMC算法往往因难以找到适合当前问题的提议分布而面临收敛缓慢的问题。为解决这一问题,本文引入了近似后验集成采样器(APES)算法,该算法采用核密度估计和径向基插值来构建自适应提议分布,从而实现链的快速收敛。APES算法对更高维度的可扩展性使其成为复杂问题的实用解决方案。所提出的方法生成一个近似后验概率,该概率紧密逼近期望分布且易于采样,从而带来更小的自相关时间和更高的链接受概率。我们在多种场景下将APES算法与采用拉伸移动的仿射不变集成采样器进行了性能比较,证明了所提方法的效率。例如,在Rosenbrock函数上,APES的自相关时间比仿射不变集成采样器小140倍。该比较展示了APES算法在从具有挑战性的分布中生成样本方面的有效性。本文提出了一种从复杂分布中生成样本的实用解决方案,同时应对了寻找合适提议分布的挑战。随着新的宇宙学巡天需要处理许多新的系统误差,该方法为即将到来的宇宙学分析时代提供了一种实用解决方案。本文提出的算法可在https://github.com/NumCosmo/NumCosmo获取。
英文摘要:
This paper proposes a novel approach to generate samples from target distributions that are difficult to sample from using Markov Chain Monte Carlo (MCMC) methods. Traditional MCMC algorithms often face slow convergence due to the difficulty in finding proposals that suit the problem at hand. To address this issue, the paper introduces the Approximate Posterior Ensemble Sampler (APES) algorithm, which employs kernel density estimation and radial basis interpolation to create an adaptive proposal, leading to fast convergence of the chains. The APES algorithm's scalability to higher dimensions makes it a practical solution for complex problems. The proposed method generates an approximate posterior probability that closely approximates the desired distribution and is easy to sample from, resulting in smaller autocorrelation times and a higher probability of acceptance by the chain. We compare the performance of the APES algorithm with the affine invariance ensemble sampler with the stretch move in various contexts, demonstrating the efficiency of the proposed method. For instance, on the Rosenbrock function, the APES presented an autocorrelation time 140 times smaller than the affine invariance ensemble sampler. The comparison showcases the effectiveness of the APES algorithm in generating samples from challenging distributions. This paper presents a practical solution to generating samples from complex distributions while addressing the challenge of finding suitable proposals. With new cosmological surveys set to deal with many new systematics, this method offers a practical solution for the upcoming era of cosmological analyses. The algorithms presented in this paper are available at https://github.com/NumCosmo/NumCosmo.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。