中文
相关论文

相关论文: The Expressive Power of a Class of Normalizing Flo…

200 篇论文

Generative flows are attractive because they admit exact likelihood optimization and efficient image synthesis. Recently, Kingma & Dhariwal (2018) demonstrated with Glow that generative flows are capable of generating high quality images.…

机器学习 · 计算机科学 2019-05-21 Emiel Hoogeboom , Rianne van den Berg , Max Welling

Due to the success of generative flows to model data distributions, they have been explored in inverse problems. Given a pre-trained generative flow, previous work proposed to minimize the 2-norm of the latent variables as a regularization…

计算机视觉与模式识别 · 计算机科学 2022-05-30 José A. Chávez

This paper begins with a description of methods for estimating image probability density functions that reflects the observation that such data is usually constrained to lie in restricted regions of the high-dimensional image space-not…

计算机视觉与模式识别 · 计算机科学 2023-11-14 Peter Tu , Zhaoyuan Yang , Richard Hartley , Zhiwei Xu , Jing Zhang , Yiwei Fu , Dylan Campbell , Jaskirat Singh , Tianyu Wang

Dimensionality reduction, a form of compression, can simplify representations of information to increase efficiency and reveal general patterns. Yet, this simplification also forfeits information, thereby reducing representational capacity.…

Visualization of turbulent flows is a powerful tool to help understand the turbulence dynamics and induced transport. However, it does not provide a quantitative description of the observed structures. In this paper, an approach to…

等离子体物理 · 物理学 2009-11-13 Benjamin A. Carreras , Irene Llerena , Luis Garcia , Ivan Calvo

Generalized models provide a framework for the study of evolution equations without specifying all functional forms. The generalized formulation of problems has been shown to facilitate the analytical investigation of local dynamics and has…

动力系统 · 数学 2014-06-24 Christian Kuehn , Stefan Siegmund , Thilo Gross

Studying the dynamics of open quantum systems can enable breakthroughs both in fundamental physics and applications to quantum engineering and quantum computation. Since the density matrix $\rho$, which is the fundamental description for…

量子物理 · 物理学 2023-06-08 Owen Dugan , Peter Y. Lu , Rumen Dangovski , Di Luo , Marin Soljačić

The recent introduction of machine learning techniques, especially normalizing flows, for the sampling of lattice gauge theories has shed some hope on improving the sampling efficiency of the traditional HMC algorithm. Naive use of…

高能物理 - 格点 · 物理学 2022-12-06 David Albandea , Luigi Del Debbio , Pilar Hernández , Richard Kenway , Joe Marsh Rossney , Alberto Ramos

Normalizing flows are a class of deep generative models that provide a promising route to sample lattice field theories more efficiently than conventional Monte Carlo simulations. In this work we show that the theoretical framework of…

高能物理 - 格点 · 物理学 2022-07-07 Michele Caselle , Elia Cellini , Alessandro Nada , Marco Panero

Many generative models originally developed in finite-dimensional Euclidean space have functional generalizations in infinite-dimensional settings. However, the extension of rectified flow to infinite-dimensional spaces remains unexplored.…

机器学习 · 计算机科学 2025-09-15 Jianxin Zhang , Clayton Scott

Variational inference relies on flexible approximate posterior distributions. Normalizing flows provide a general recipe to construct flexible variational posteriors. We introduce Sylvester normalizing flows, which can be seen as a…

机器学习 · 统计学 2019-02-21 Rianne van den Berg , Leonard Hasenclever , Jakub M. Tomczak , Max Welling

Modern deep generative models can now produce high-quality synthetic samples that are often indistinguishable from real training data. A growing body of research aims to understand why recent methods, such as diffusion and flow matching…

机器学习 · 计算机科学 2025-12-03 Quentin Bertrand , Anne Gagneux , Mathurin Massias , Rémi Emonet

Current-voltage measurements of type-II superconductors are described by a coarse-grained model of superconducting vortex dynamics. We find that the power spectra of the voltage fluctuations, and the noise power, are related to the large…

统计力学 · 物理学 2007-05-23 Kevin E. Bassler , Joern Davidsen , Maya Paczuski

This paper studies the cooperative learning of two generative flow models, in which the two models are iteratively updated based on the jointly synthesized examples. The first flow model is a normalizing flow that transforms an initial…

机器学习 · 统计学 2022-05-17 Jianwen Xie , Yaxuan Zhu , Jun Li , Ping Li

Normalizing flows are an essential alternative to GANs for generative modelling, which can be optimized directly on the maximum likelihood of the dataset. They also allow computation of the exact latent vector corresponding to an image…

机器学习 · 计算机科学 2021-08-10 Sandeep Nagar , Marius Dufraisse , Girish Varma

Complex networks have acquired a great popularity in recent years, since the graph representation of many natural, social and technological systems is often very helpful to characterize and model their phenomenology. Additionally, the…

物理与社会 · 物理学 2009-02-06 Filippo Radicchi , Alain Barrat , Santo Fortunato , Jose J. Ramasco

We identify incompressible planar linear flows that are generalizations of the well known one-parameter family characterized by the ratio of in-plane extension to (out-of-plane) vorticity. The latter `canonical' family is classified into…

流体动力学 · 物理学 2022-06-16 Sabarish V Narayanan , Ganesh Subramanian

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

机器学习 · 计算机科学 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues: 1) If the target distribution is manifold, due to the unmatch between the dimensions of the latent target distribution…

机器学习 · 计算机科学 2024-04-24 Qinglong Meng , Chongkun Xia , Xueqian Wang

Normalizing flows (NFs) provide a powerful tool to construct an expressive distribution by a sequence of trackable transformations of a base distribution and form a probabilistic model of underlying data. Rotation, as an important quantity…

计算机视觉与模式识别 · 计算机科学 2023-04-11 Yulin Liu , Haoran Liu , Yingda Yin , Yang Wang , Baoquan Chen , He Wang