Stochastic variational inference and its derivatives in the form of variational autoencoders enjoy the ability to perform Bayesian inference on large datasets in an efficient manner. However, performing inference with a VAE requires a certain design choice (i.e. reparameterization trick) to allow unbiased and low variance gradient estimation, restricting the types of models that can be created. To overcome this challenge, an alternative estimator based on natural evolution strategies is proposed. This estimator does not make assumptions about the kind of distributions used, allowing for the creation of models that would otherwise not have been possible under the VAE framework.

翻译：随机变分推断及其衍生的变分自编码器具备在大型数据集上高效进行贝叶斯推断的能力。然而，使用变分自编码器进行推断需要特定的设计选择（如重参数化技巧）以实现无偏且低方差的梯度估计，这限制了可构建模型的类型。为克服这一挑战，本文提出一种基于自然进化策略的替代估计器。该估计器无需对所使用的分布类型做任何假设，从而支持创建在变分自编码器框架下原本无法实现的模型。