Neural Autoregressive Distribution Estimation
We present Neural Autoregressive Distribution Estimation (NADE) models, which are neural network architectures applied to the problem of unsupervised distribution and density estimation. They leverage the probability product rule and a weight sharing scheme inspired from restricted Boltzmann machines, to yield an estimator that is both tractable and has good generalization performance. We discuss how they achieve competitive performance in modeling both binary and real-valued observations. We also present how deep NADE models can be trained to be agnostic to the ordering of input dimensions used by the autoregressive product rule decomposition. Finally, we also show how to exploit the topological structure of pixels in images using a deep convolutional architecture for NADE.
Code (3)
Tasks
Density EstimationImage GenerationSimilar Papers 제목 키워드 기반
Neural Autoregressive Flows
Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-bas…
Density EstimationSpeech SynthesisProbabilistic Classification by Density Estimation Using Gaussian Mixture Model and Masked Autoregressive Flow
Density estimation, which estimates the distribution of data, is an important category of probabilistic machine learning. A family of density estimators is mixture models, such as Gaussian Mixture Model (GMM) by expectat…
ClassificationDensity EstimationNormalising FlowsBayesian autoregressive spectral estimation
Autoregressive (AR) time series models are widely used in parametric spectral estimation (SE), where the power spectral density (PSD) of the time series is approximated by that of the \emph{best-fit} AR model, which is a…
Time SeriesTime Series AnalysisGravitational-wave parameter estimation with autoregressive neural network flows
We introduce the use of autoregressive normalizing flows for rapid likelihood-free inference of binary black hole system parameters from gravitational-wave data with deep neural networks. A normalizing flow is an inverti…
parameter estimationAutoregressive Quantile Flows for Predictive Uncertainty Estimation
Numerous applications of machine learning involve representing probability distributions over high-dimensional data. We propose autoregressive quantile flows, a flexible class of normalizing flow models trained using a n…
Density Estimationobject-detectionObject Detectionregression+3