论文标题
学习用于训练和评估基于能量的模型的Stein差异
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
论文作者
论文摘要
我们提出了一种评估和训练非标准密度模型的新方法。我们的方法仅需要访问未归一化模型的对数密度的梯度。我们估计数据密度$ p（x）$与模型密度$ q（x）$之间的Stein差异。我们使用神经网络对此功能进行参数化，并拟合其参数以最大化差异。这产生了一种新颖的合适性测试，该测试的表现优于高维数据上的现有方法。此外，优化$ Q（x）$以最大程度地减少这种差异会产生一种新的训练模型的新方法，该模型比现有方法更优雅地扩展。学习和比较模型的能力是提出方法的独特功能。
We present a new method for evaluating and training unnormalized density models. Our approach only requires access to the gradient of the unnormalized model's log-density. We estimate the Stein discrepancy between the data density $p(x)$ and the model density $q(x)$ defined by a vector function of the data. We parameterize this function with a neural network and fit its parameters to maximize the discrepancy. This yields a novel goodness-of-fit test which outperforms existing methods on high dimensional data. Furthermore, optimizing $q(x)$ to minimize this discrepancy produces a novel method for training unnormalized models which scales more gracefully than existing methods. The ability to both learn and compare models is a unique feature of the proposed method.
