normflows: A pytorch package for normalizing flows

V Stimper, D Liu, A Campbell, V Berenz, L Ryll… - arXiv preprint arXiv …, 2023 - arxiv.org
Normalizing flows model probability distributions through an expressive tractable density.
They transform a simple base distribution, such as a Gaussian, through a sequence of …

Whitening convergence rate of coupling-based normalizing flows

F Draxler, C Schnörr, U Köthe - Advances in Neural …, 2022 - proceedings.neurips.cc
Coupling-based normalizing flows (eg RealNVP) are a popular family of normalizing flow
architectures that work surprisingly well in practice. This calls for theoretical understanding …

Self-supervised normalizing flows for image anomaly detection and localization

LL Chiu, SH Lai - Proceedings of the IEEE/CVF conference …, 2023 - openaccess.thecvf.com
Image anomaly detection aims to detect out-of-distribution instances. Most existing methods
treat anomaly detection as an unsupervised task because anomalous training data and …

[HTML][HTML] A conditional normalizing flow for accelerated multi-coil MR imaging

J Wen, R Ahmad, P Schniter - Proceedings of machine learning …, 2023 - ncbi.nlm.nih.gov
Accelerated magnetic resonance (MR) imaging attempts to reduce acquisition time by
collecting data below the Nyquist rate. As an ill-posed inverse problem, many plausible …

Generative invertible quantum neural networks

A Rousselot, M Spannowsky - SciPost Physics, 2024 - scipost.org
Abstract Invertible Neural Networks (INN) have become established tools for the simulation
and generation of highly complex data. We propose a quantum-gate algorithm for a …

Active learning for the design of polycrystalline textures using conditional normalizing flows

MO Buzzy, DM de Oca Zapiain, AP Generale… - Acta Materialia, 2025 - Elsevier
Generative modeling has opened new avenues for solving previously intractable materials
design problems. However, these new opportunities are accompanied by a drastic increase …

PET-3DFlow: A Normalizing Flow Based Method for 3D PET Anomaly Detection

Z Xiong, Q Ding, Y Zhao, X Zhang - International Workshop on …, 2023 - Springer
Abstract Anomaly detection of Positron Emission Tomography (PET) are important tasks for
clinical diagnosis and treatments. For 3D PET images, it is arduous for the annotations of …

Robustly Train Normalizing Flows via KL Divergence Regularization

K Song, R Solozabal, H Li, M Takáč, L Ren… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
In this paper, we find that the training of Normalizing Flows (NFs) are easily affected by the
outliers and a small number (or high dimensionality) of training samples. To solve this …

Invertible neural networks for inverse design of CTLE in high-speed channels

MA Dolatsara, H Yu, JA Hejase… - 2020 IEEE Electrical …, 2020 - ieeexplore.ieee.org
Designing CTLE of high-speed channels can be complicated and time consuming. To
alleviate this issue, this paper investigates the invertible neural networks (INNs) for inverse …

Efficient Sound Field Reconstruction with Conditional Invertible Neural Networks

X Karakonstantis, E Fernandez-Grande… - arXiv preprint arXiv …, 2024 - arxiv.org
In this study, we introduce a method for estimating sound fields in reverberant environments
using a conditional invertible neural network (CINN). Sound field reconstruction can be …