论文标题
半自动回调能量流：探索归一化流量的无似然培训
Semi-Autoregressive Energy Flows: Exploring Likelihood-Free Training of Normalizing Flows
论文作者
论文摘要
由于需要计算雅各布人的计算昂贵决定因素，因此训练归一化流量生成模型可能具有挑战性。本文研究了对流量的可能性训练，并提出了能源目标，这是基于适当评分规则的替代样本损失。能源目标是无决定性的，并支持灵活的模型体系结构，这些模型体系结构与最大似然训练不容易兼容，包括半自动进取的能量流，这是一个新型的模型家族，可在完全自动回归和非运动型模型之间进行插值。能量流具有竞争性样本质量，后推断和相对于基于似然流的产生速度；这种性能与原木样估计的质量相关，这些估计通常非常差。我们的发现质疑将最大可能性用作客观或指标的使用，并有助于科学研究其在生成建模中的作用。
Training normalizing flow generative models can be challenging due to the need to calculate computationally expensive determinants of Jacobians. This paper studies the likelihood-free training of flows and proposes the energy objective, an alternative sample-based loss based on proper scoring rules. The energy objective is determinant-free and supports flexible model architectures that are not easily compatible with maximum likelihood training, including semi-autoregressive energy flows, a novel model family that interpolates between fully autoregressive and non-autoregressive models. Energy flows feature competitive sample quality, posterior inference, and generation speed relative to likelihood-based flows; this performance is decorrelated from the quality of log-likelihood estimates, which are generally very poor. Our findings question the use of maximum likelihood as an objective or a metric, and contribute to a scientific study of its role in generative modeling.
