论文标题
使用神经网络对分区功能进行近似采样和估计
Approximate sampling and estimation of partition functions using neural networks
论文作者
论文摘要
我们考虑了从已知的分布到归一化常数的采样紧密相关的问题，并估算了所述标准化常数。我们展示了如何将变异自动编码器（VAE）应用于此任务。在其标准应用中，VAE经过培训以适合从棘手的分布中获取的数据。我们将逻辑倒转并训练VAE以符合简单且可拖动的分布，假设具有归一化的复杂而棘手的潜在分布。此过程无需使用训练数据或马尔可夫链蒙特卡洛采样即可构建近似值。我们在三个示例中说明了我们的方法：ISING模型，图形聚类和排名。
We consider the closely related problems of sampling from a distribution known up to a normalizing constant, and estimating said normalizing constant. We show how variational autoencoders (VAEs) can be applied to this task. In their standard applications, VAEs are trained to fit data drawn from an intractable distribution. We invert the logic and train the VAE to fit a simple and tractable distribution, on the assumption of a complex and intractable latent distribution, specified up to normalization. This procedure constructs approximations without the use of training data or Markov chain Monte Carlo sampling. We illustrate our method on three examples: the Ising model, graph clustering, and ranking.
