Optimal Simulated Annealing for Partition Function Estimation

2026-09-17

AI Summary

本文通过非自适应模拟退火算法有效估计吉布斯分布的配分函数，提供最高效方法，并证明了该算法在广泛参数范围内的最优性。

Abstract

In this note, we give a simple analysis of a non-adaptive simulated annealing algorithm for estimating the partition function of Gibbs distributions. This yields the most efficient reduction of this kind so far. We also establish lower bounds for both general and non-adaptive algorithms, showing that our algorithm is optimal over a broad range of parameters.

Problem

• partition function
• Gibbs distributions
• simulated annealing

Innovation

• non-adaptive simulated annealing
• partition function
• Gibbs distributions
• optimal algorithm