Normalizing Flows: An Introduction and Review of Current Methods

2019/08/31 by Ivan Kobyzev, Simon J. D. Prince, Marcus A. Brubaker · 10 citations
Computer Science · Mathematics · #cs.LG #stat.ML

paper · pdf · doi:10.1109/tpami.2020.2992934

This paper appears in: IEEE Transactions on Pattern Analysis and Machine Intelligence On page(s): 1-16 Print ISSN: 0162-8828 Online ISSN: 0162-8828

arxiv created 2020/06/06 · arxiv updated 2020/06/09

Abstract

Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature around the construction and use of Normalizing Flows for distribution learning. We aim to provide context and explanation of the models, review current state-of-the-art literature, and identify open questions and promising future directions.

Cited by

• Self-Aware Object Detection via Degradation Manifolds
• Profiling systematic uncertainties in Simulation-Based Inference with Factorizable Normalizing Flows
• High-dimensional reliability-based design optimization using stochastic emulators
• Safe Urban Traffic Control via Uncertainty-Aware Conformal Prediction and World-Model Reinforcement Learning
• Physical Transformer
• Evaluating Learned Query Performance Prediction Models at LinkedIn: Challenges, Opportunities, and Findings
• A Comprehensive Survey of Synthetic Tabular Data Generation
• Diffusion-based supervised learning of generative models for efficient sampling of multimodal distributions
• Reconstruction of angular correlations in the associated top quark and the dark matter mediator production
• On the minimax optimality of Flow Matching through the connection to kernel density estimation