Continuous Relaxations for Discrete Hamiltonian Monte Carlo
Continuous Relaxations for Discrete Hamiltonian Monte Carlo
复制标题
DOI：
--
复制
发表时间：
2012-12
影响因子：
6.2
通讯作者：
Yichuan Zhang;Charles Sutton;A. Storkey;Zoubin Ghahramani
中科院分区：
文献类型：
--
作者：
Yichuan Zhang;Charles Sutton;A. Storkey;Zoubin Ghahramani
连续放松在离散优化中起着重要的作用，但在近似概率推论中没有太多使用。在这里，我们表明，高斯积分窍门的一般形式使得可以将一类广泛的离散变量无向模型转换为完全连续的系统。连续表示允许使用基于梯度的汉密尔顿蒙特卡洛进行推断，导致新的估计归一化常数（分区函数）的方式，并且一般而言，为困难的离散系统中的推断提供了许多新途径。我们在许多说明性问题上证明了其中一些连续的放松推理算法。
Continuous relaxations play an important role in discrete optimization, but have not seen much use in approximate probabilistic inference. Here we show that a general form of the Gaussian Integral Trick makes it possible to transform a wide class of discrete variable undirected models into fully continuous systems. The continuous representation allows the use of gradient-based Hamiltonian Monte Carlo for inference, results in new ways of estimating normalization constants (partition functions), and in general opens up a number of new avenues for inference in difficult discrete systems. We demonstrate some of these continuous relaxation inference algorithms on a number of illustrative problems.