Deep Nonparametric Estimation of Discrete Conditional Distributions via Smoothed Dyadic Partitioning
arXiv:1702.07398
Abstract
We present an approach to deep estimation of discrete conditional probability distributions. Such models have several applications, including generative modeling of audio, image, and video data. Our approach combines two main techniques: dyadic partitioning and graph-based smoothing of the discrete space. By recursively decomposing each dimension into a series of binary splits and smoothing over the resulting distribution using graph-based trend filtering, we impose a strict structure to the model and achieve much higher sample efficiency. We demonstrate the advantages of our model through a series of benchmarks on both synthetic and real-world datasets, in some cases reducing the error by nearly half in comparison to other popular methods in the literature. All of our models are implemented in Tensorflow and publicly available at https://github.com/tansey/sdp .
References in corpus (7)
- DRAW: A Recurrent Neural Network For Image Generation
- Deep Survival Analysis
- PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
- Multiscale spatial density smoothing: an application to large-scale radiological survey and anomaly detection
- Predicting Surgery Duration with Neural Heteroscedastic Regression
- Adaptive Risk Bounds in Univariate Total Variation Denoising and Trend Filtering
- Learning Diverse Image Colorization