normflows: A PyTorch Package for Normalizing Flows

Abstract

Normalizing flows model probability distributions through an expressive tractable density. They transform a simple base distribution, such as a Gaussian, through a sequence of invertible functions, which are referred to as layers. These layers typically use neural networks to become very expressive. Flows are ubiquitous in machine learning and have been applied to image generation, text modeling, variational inference, approximating Boltzmann distributions, and many other problems. Here, we present normflows, a Python package for normalizing flows. It allows to build normalizing flow models from a suite of base distributions, flow layers, and neural networks. The package is implemented in the popular deep learning framework PyTorch, which simplifies the integration of flows in larger machine learning models or pipelines. It supports most of the common normalizing flow architectures, such as Real NVP, Glow, Masked Autoregressive Flows, Neural Spline Flows, Residual Flows, and many more. The package can be easily installed via pip and the code is publicly available on GitHub.

References in corpus (4)

• TensorFlow Distributions
• Stochastic Normalizing Flows
• Densely connected normalizing flows
• Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling

Cited by in corpus (11)

• Mamba time series forecasting with uncertainty quantification
• Flow Matching for Atmospheric Retrieval of Exoplanets: Where Reliability meets Adaptive Noise Levels
• StarFlow: Leveraging Normalizing Flows for Stellar Age Estimation in SDSS-V DR19
• Variational inference based on a subclass of closed skew normals
• Detecting Modeling Bias with Continuous Time Flow Models on Weak Lensing Maps
• Search for Beyond the Standard Model physics with anomaly detection in multilepton final states in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Avoiding subtraction and division of stochastic signals using normalizing flows: NFdeconvolve
• Density Estimation via Binless Multidimensional Integration
• Data-Driven Predictions for Dark Photon and Millicharged Particle Production
• On the performance of multi-fidelity and reduced-dimensional neural emulators for inference of physiological boundary conditions
• NeuMC -- a package for neural sampling for lattice field theories