科研之友
微信
新浪微博
Facebook
分享链接
摘要
Consider a family of distributions {pi(beta)} where X similar to pi(beta) means that P(X = x) = exp(-beta H(x))/Z(beta). Here Z(beta) is the proper normalizing constant, equal to Sigma(x) exp(-beta H(x)). Then {pi(beta)} is known as a Gibbs distribution, and Z(beta) is the partition function. This work presents a new method for approximating the partition function to a specified level of relative accuracy using only a number of samples, that is, O(ln(Z(beta) ln(ln(Z(beta)))) when Z(0) >= 1. This is a sharp improvement over previous, similar approaches that used a much more complicated algorithm, requiring O(ln(Z(beta) ln(ln(Z(beta)))(5)) samples.
- 出版日期2015-4
