arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1907.11985stat.COcs.LGmath.OC
收藏

随机最优化的Wang-Landau算法及其加速

The Wang-Landau Algorithm as Stochastic Optimization and Its Acceleration

Department of Statistics, Harvard University(哈佛大学统计系)

Chenguang Dai, Jun S. Liu

摘要:

我们表明,Wang-Landau算法可以制定为一个随机梯度下降算法最小化一个光滑和凸的目标函数,其中的梯度估计使用马尔可夫链蒙特卡罗迭代。优化公式为我们提供了一种新的方法来建立Wang-Landau算法的收敛速度,通过利用几乎可以肯定的事实,密度估计(在对数尺度上)保持在一个紧凑的集合中,目标函数是强凸的。优化的观点促使我们使用流行的工具,包括动量方法和自适应学习率方法来提高Wang-Landau算法的效率。我们在二维Ising模型和二维十态Potts模型上证明了加速Wang-Landau算法。

英文摘要:

We show that the Wang-Landau algorithm can be formulated as a stochastic gradient descent algorithm minimizing a smooth and convex objective function, of which the gradient is estimated using Markov chain Monte Carlo iterations. The optimization formulation provides us a new way to establish the convergence rate of the Wang-Landau algorithm, by exploiting the fact that almost surely, the density estimates (on the logarithmic scale) remain in a compact set, upon which the objective function is strongly convex. The optimization viewpoint motivates us to improve the efficiency of the Wang-Landau algorithm using popular tools including the momentum method and the adaptive learning rate method. We demonstrate the accelerated Wang-Landau algorithm on a two-dimensional Ising model and a two-dimensional ten-state Potts model.

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。

↑