paper-with-me

Papers

An Empirical Comparison of GANs and Normalizing Flows for Density Estimation

2020-06-17 · Tianci Liu, Jeffrey Regier

Generative adversarial networks (GANs) and normalizing flows are both approaches to density estimation that use deep neural networks to transform samples from an uninformative prior distribution to an approximation of the data distribution. There is great interest in both for general-purpose statistical modeling, but the two approaches have seldom been compared to each other for modeling non-image data. The difficulty of computing likelihoods with GANs, which are implicit models, makes conducting such a comparison challenging. We work around this difficulty by considering several low-dimensional synthetic datasets. An extensive grid search over GAN architectures, hyperparameters, and training procedures suggests that no GAN is capable of modeling our simple low-dimensional data well, a task we view as a prerequisite for an approach to be considered suitable for general-purpose statistical modeling. Several normalizing flows, on the other hand, excelled at these tasks, even substantially outperforming WGAN in terms of Wasserstein distance -- the metric that WGAN alone targets. Scientists and other practitioners should be wary of relying on WGAN for applications that require accurate density estimation.

📄 PDF Abstract BibTeX arXiv:2006.10175

Code (1)

lliutianc/gan-flow 공식 구현 pytorch

Tasks

Density Estimation

Methods 이 논문이 사용한 방법론

Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
WGAN Wasserstein GAN, or WGAN, is a type of generative adversarial network that minimizes an approximation of the Earth-Mover's distance (EM) rather than the Jensen-Shannon…

Similar Papers 제목 키워드 기반

Continuous-Time Flows for Efficient Inference and Density Estimation

2017-09-04 · ICML 2018 7 · Changyou Chen, Chunyuan Li, Liqun Chen, Wenlin Wang 외

Two fundamental problems in unsupervised learning are efficient inference for latent-variable models and robust density estimation based on large amounts of unlabeled data. Algorithms for the two tasks, such as normalizi…

Density Estimation

Flows for simultaneous manifold learning and density estimation

2020-03-31 · NeurIPS 2020 12 · Johann Brehmer, Kyle Cranmer

We introduce manifold-learning flows (M-flows), a new class of generative models that simultaneously learn the data manifold as well as a tractable probability density on that manifold. Combining aspects of normalizing f…

DenoisingDensity EstimationDimensionality ReductionOut-of-Distribution Detection

Training Normalizing Flows from Dependent Data

2022-09-29 · Matthias Kirchler, Christoph Lippert, Marius Kloft

Normalizing flows are powerful non-parametric statistical models that function as a hybrid between density estimators and generative models. Current learning algorithms for normalizing flows assume that data points are s…

Density Estimation

Empirical evaluation of normalizing flows in Markov Chain Monte Carlo

2024-12-22 · David Nabergoj, Erik Štrumbelj

Recent advances in MCMC use normalizing flows to precondition target distributions and enable jumps to distant regions. However, there is currently no systematic comparison of different normalizing flow architectures for…

Flows for Flows: Training Normalizing Flows Between Arbitrary Distributions with Maximum Likelihood Estimation

2022-11-04 · Samuel Klein, John Andrew Raine, Tobias Golling

Normalizing flows are constructed from a base distribution with a known density and a diffeomorphism with a tractable Jacobian. The base density of a normalizing flow can be parameterised by a different normalizing flow,…