A Triangular Network For Density Estimation

2020/04/30 by Xi-Lin Li, Li, Xi-Lin
Computer Science · #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2004.14593

openalex publication_date 2020/04/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We report a triangular neural network implementation of neural autoregressive flow (NAF). Unlike many universal autoregressive density models, our design is highly modular, parameter economy, computationally efficient, and applicable to density estimation of data with high dimensions. It achieves state-of-the-art bits-per-dimension indices on MNIST and CIFAR-10 (about 1.1 and 3.7, respectively) in the category of general-purpose density estimators.

Citations

• Independent component analysis: algorithms and applications
• Block Neural Autoregressive Flow
• FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models

Related

• Masked Autoregressive Flow for Density Estimation
• Block Neural Autoregressive Flow
• A Deep and Tractable Density Estimator
• Neural Autoregressive Distribution Estimation
• HCNAF: Hyper-Conditioned Neural Autoregressive Flow and its Application\n for Probabilistic Occupancy Map Forecasting