论文标题
使用混合模型稳定可逆神经网络
Stabilizing Invertible Neural Networks Using Mixture Models
论文作者
论文摘要
在本文中，我们分析了可逆神经网络的特性，这些神经网络提供了一种解决反问题的方法。我们的主要重点在于研究和控制相应反向网络的Lipschitz常数。没有这样的控制，数值模拟就容易出错，并且与传统方法相比并没有得到太多。幸运的是，我们的分析表明，将潜在分布从标准的正常分布更改为高斯混合物模型可以解决爆炸Lipschitz常数的问题。实际上，数值模拟证实，这种修饰会导致多模式应用中的采样质量显着提高。
In this paper, we analyze the properties of invertible neural networks, which provide a way of solving inverse problems. Our main focus lies on investigating and controlling the Lipschitz constants of the corresponding inverse networks. Without such an control, numerical simulations are prone to errors and not much is gained against traditional approaches. Fortunately, our analysis indicates that changing the latent distribution from a standard normal one to a Gaussian mixture model resolves the issue of exploding Lipschitz constants. Indeed, numerical simulations confirm that this modification leads to significantly improved sampling quality in multimodal applications.
