paper-with-me

Papers

Solving ODE with Universal Flows: Approximation Theory for Flow-Based Models

2020-02-26 · ICLR Workshop DeepDiffEq 2019 12 · Chin-wei Huang, Laurent Dinh, Aaron Courville

Normalizing flows are powerful invertible probabilistic models that can be used to translate two probability distributions, in a way that allows us to efficiently track the change of probability density. However, to trade for computational efficiency in sampling and in evaluating the log-density, special parameterization designs have been proposed at the cost of representational expressiveness. In this work, we propose to use ODEs as a framework to establish universal approximation theory for certain families of flow-based models.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows

2021-10-08 · Michael Puthawala, Matti Lassas, Ivan Dokmanić, Maarten de Hoop

We study approximation of probability measures supported on $n$-dimensional manifolds embedded in $\mathbb{R}^m$ by injective flows -- neural networks composed of invertible flows and injective layers. We show that in ge…

Universal Approximation of Residual Flows in Maximum Mean Discrepancy

2021-03-10 · ICML Workshop INNF 2021 7 · Zhifeng Kong, Kamalika Chaudhuri

Normalizing flows are a class of flexible deep generative models that offer easy likelihood computation. Despite their empirical success, there is little theoretical understanding of their expressiveness. In this work, w…

Universality of parametric Coupling Flows over parametric diffeomorphisms

2022-02-07 · Junlong Lyu, Zhitang Chen, Chang Feng, Wenjing Cun 외

Invertible neural networks based on Coupling Flows CFlows) have various applications such as image synthesis and data compression. The approximation universality for CFlows is of paramount importance to ensure the model …

Bayesian OptimizationData CompressionImage Generation

Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization

2020-12-10 · ICLR 2021 1 · Chin-wei Huang, Ricky T. Q. Chen, Christos Tsirigotis, Aaron Courville

Flow-based models are powerful tools for designing probabilistic models with tractable density. This paper introduces Convex Potential Flows (CP-Flow), a natural and efficient parameterization of invertible models inspir…

Density EstimationVariational Inference

Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations

2026-05-21 · Shuang Chen, Juncai He, Xue-Cheng Tai arxiv

We introduce an abstract neural flow framework for neural networks and neural operators. The framework contains two continuous-depth models, namely neural flows with composition and separation structures, and covers both…