Amortized Population Gibbs Samplers with Neural Sufficient Statistics
Amortized Population Gibbs Samplers with Neural Sufficient Statistics
复制标题
DOI：
--
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Hao Wu;Heiko Zimmermann;Eli Sennesh;T. Le;Jan-Willem van de Meent
中科院分区：
文献类型：
--
作者：
Hao Wu;Heiko Zimmermann;Eli Sennesh;T. Le;Jan-Willem van de Meent
我们发展了摊销总体吉布斯(APG)采样器，这是一类可扩展的方法，将结构化变分推理框架为自适应重要性抽样。APG采样器通过迭代对低维变量块的更新来构建高维方案。我们通过最小化相对于条件后验知识的包含KL发散来训练每个条件建议。为了适当地解释输入数据的大小，我们开发了一种新的基于神经充分统计的参数化。实验表明，APG采样器可以在无监督的情况下训练高结构的深度生成模型，并且与标准的自动编码变分方法相比，推理精度有了很大的提高。
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.