Amortized variational methods have proven difficult to scale to structured problems, such as inferring positions of multiple objects from video images. We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frames structured variational inference as adaptive importance sampling. APG samplers construct high-dimensional proposals by iterating over updates to lower-dimensional blocks of variables. We train each conditional proposal by minimizing the inclusive KL divergence with respect to the conditional posterior. To appropriately account for the size of the input data, we develop a new parameterization in terms of neural sufficient statistics. Experiments show that APG samplers can train highly structured deep generative models in an unsupervised manner, and achieve substantial improvements in inference accuracy relative to standard autoencoding variational methods.
翻译:分解变异方法证明难以缩小到结构性问题,例如从视频图像中推断多个对象的位置。我们开发了分解人口Gibbs(APG)采样器,这是一组可伸缩的方法,将结构变异推法作为适应重要性抽样。APG采样器通过对低维变量区块的更新进行迭代来构建高维建议。我们通过最大限度地减少与有条件后继器有关的包容性KL差异来培训每个有条件的建议。为了适当计算输入数据的规模,我们开发了神经充足统计数据的新参数。实验显示,APG采样器可以以不受监督的方式培养结构高度深厚的基因模型,并大大改进与标准的自动编码变异方法相比的推断准确性。