Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization
Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization
复制标题
DOI：
--
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Aditya Grover;Stefano Ermon
中科院分区：
文献类型：
--
作者：
Aditya Grover;Stefano Ermon
压缩传感技术能够通过低维投影有效地获取和恢复稀疏的高维数据信号。在这项工作中，我们提出了不确定性自动编码器，这是一个受压缩感知启发的无监督表示学习框架。我们将低维投影视为自动编码器的噪声潜在表示，并直接学习获取(即编码)和摊销恢复(即解码)过程。我们的学习目标是优化数据点和潜在表示之间的互信息的易处理的变分下界。我们展示了我们的框架如何为降维、压缩感知和产生式建模中的几个研究方向提供统一的处理。实验证明，在高维数据集的统计压缩传感任务中，我们比竞争对手的方法平均提高了32%。
Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised representation learning inspired by compressed sensing. We treat the low-dimensional projections as noisy latent representations of an autoencoder and directly learn both the acquisition (i.e., encoding) and amortized recovery (i.e., decoding) procedures. Our learning objective optimizes for a tractable variational lower bound to the mutual information between the datapoints and the latent representations. We show how our framework provides a unified treatment to several lines of research in dimensionality reduction, compressed sensing, and generative modeling. Empirically, we demonstrate a 32% improvement on average over competing approaches for the task of statistical compressed sensing of high-dimensional datasets.